© 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. 117734
    Prev
    Next
    INDEX
    Explanations

    HTML PUBLIC DOCTYPE

    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
     incendio
    -0.82
    tilage
    -0.77
    명
    -0.67
     baj
    -0.67
    égard
    -0.67
     Neri
    -0.66
     Salón
    -0.66
     spad
    -0.65
    ubscribe
    -0.65
     sopa
    -0.65
    POSITIVE LOGITS
    oxane
    0.77
     außen
    0.71
    flg
    0.71
     plaid
    0.68
    ᵥ
    0.66
     resentment
    0.66
     characters
    0.66
    acetic
    0.65
    operands
    0.65
    itet
    0.64
    Activations Density 0.075%

    No Known Activations