© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14042
    Prev
    Next
    INDEX
    Explanations

    humanity's future or existential threat

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

    This neuron responds to the key content words—major nouns, verbs, and adjectives—that carry the main argumentative or descriptive substance of a serious expository or opinion‐style text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     envoyer
    -1.37
    ³/
    -1.30
     ہے۔
    -1.29
     obtenir
    -1.26
     ausser
    -1.25
     nästan
    -1.23
     متن
    -1.21
    ࣪
    -1.20
    ']").
    -1.20
    rifft
    -1.17
    POSITIVE LOGITS
     we
    2.33
     will
    2.09
     our
    1.88
     or
    1.63
     if
    1.39
     sehr
    1.38
     but
    1.31
     große
    1.28
     as
    1.23
     ourselves
    1.22
    Activations Density 0.024%

    No Known Activations