© 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. 22-GEMMASCOPE-RES-131K
    7. 38410
    Prev
    Next
    INDEX
    Explanations

    everyone taking action

    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_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
     also
    -1.19
     often
    -1.16
     multe
    -1.10
     sometimes
    -1.10
    celotti
    -1.08
    いつも
    -1.04
    wyneth
    -0.98
     always
    -0.95
     tutta
    -0.94
    何でも
    -0.94
    POSITIVE LOGITS
     their
    2.09
     Everyone
    1.72
    各自
    1.62
     EVERYONE
    1.59
     одина
    1.50
     except
    1.46
     Everybody
    1.41
    それぞれの
    1.39
    Everyone
    1.30
    それぞれ
    1.30
    Activations Density 0.058%

    No Known Activations