© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60624
    Prev
    Next
    INDEX
    Explanations

    tissue differentiation and annealing

    np_acts-logits-general · gemini-2.5-flash-lite

    specialized terminology or proper nouns that denote specific entities like substances, organisms, businesses, or technical terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on content‐heavy nouns—especially proper names (people, places, organizations) and technical or domain‐specific terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.64
     certains
    -1.53
     certaines
    -1.46
    olding
    -1.38
     già
    -1.37
     Preferencias
    -1.34
     temperat
    -1.34
    vamo
    -1.30
     alcuni
    -1.28
    　　“
    -1.27
    POSITIVE LOGITS
     २०
    1.33
     Getränke
    1.30
    aná
    1.27
    ANIEL
    1.27
     the
    1.27
     primeiros
    1.23
     berühm
    1.23
    쨩
    1.23
     only
    1.22
    ଷ
    1.21
    Activations Density 0.134%

    No Known Activations