© 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. 34-GEMMASCOPE-RES-131K
    7. 78417
    Prev
    Next
    INDEX
    Explanations

    is/am/was followed by state or 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_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
    📓
    -0.93
    HttpEntity
    -0.88
    ͏
    -0.86
    ck
    -0.85
    `${
    -0.85
    €™
    -0.85
    styp
    -0.82
    tigheter
    -0.81
     عربي
    -0.81
    endsection
    -0.80
    POSITIVE LOGITS
     into
    1.15
     oblivion
    1.05
     anyways
    1.02
     előtt
    0.94
     also
    0.85
    panda
    0.84
     aware
    0.84
     anyway
    0.81
     termed
    0.77
     anyhow
    0.77
    Activations Density 0.065%

    No Known Activations