© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25313
    Prev
    Next
    INDEX
    Explanations

    introducing benefits and calls to 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
     and
    -1.95
     foran
    -1.48
     bluz
    -1.45
    ——–
    -1.45
    …]
    -1.41
    wakili
    -1.41
    ⿻
    -1.40
    ———-
    -1.38
     etui
    -1.38
     doon
    -1.37
    POSITIVE LOGITS
    This
    1.62
     will
    1.50
    this
    1.46
     you
    1.41
    has
    1.40
     is
    1.40
    can
    1.31
    is
    1.30
    in
    1.29
    il
    1.29
    Activations Density 0.014%

    No Known Activations