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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109872
    Prev
    Next
    INDEX
    Explanations

    asking for something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     котором
    -1.30
     которое
    -1.30
     to
    -1.26
     officielles
    -1.25
     during
    -1.23
     from
    -1.23
    作为一个
    -1.21
     for
    -1.20
     although
    -1.20
    nexpected
    -1.17
    POSITIVE LOGITS
     a
    2.67
     something
    2.05
     more
    1.58
     secrétaire
    1.37
    ༈
    1.35
     an
    1.30
     anjo
    1.30
     trás
    1.26
     député
    1.23
     things
    1.21
    Activations Density 0.073%

    No Known Activations