© 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. 101005
    Prev
    Next
    INDEX
    Explanations

    informations and artworks

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

    The neuron strongly activates on content‐bearing nouns (especially proper nouns and key object nouns).

    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
     eşofman
    -2.84
     desenli
    -2.83
     buruk
    -2.81
    们
    -2.70
    厹
    -2.67
     dekoratif
    -2.66
     katk
    -2.61
     aksesuar
    -2.55
     lucu
    -2.53
    ‘‘
    -2.47
    POSITIVE LOGITS
    胧
    2.81
    怼
    2.67
     What
    2.53
    ing
    2.47
    ة
    2.47
     Some
    2.44
     Importantly
    2.42
     欣赏
    2.36
    d
    2.31
    ttemberg
    2.25
    Activations Density 0.008%

    No Known Activations