© 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. 78487
    Prev
    Next
    INDEX
    Explanations

    academic journal

    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
     bourgeo
    -0.80
     Mankind
    -0.79
    枚
    -0.77
     Emits
    -0.77
     garam
    -0.76
    чих
    -0.74
     Polity
    -0.73
     Enabled
    -0.73
     annum
    -0.72
     bior
    -0.72
    POSITIVE LOGITS
    Mostly
    1.02
     Mostly
    0.80
     ничего
    0.80
    を使って
    0.79
    dol
    0.77
    pru
    0.75
     ещё
    0.75
    (/
    0.75
    いろんな
    0.73
    墅
    0.72
    Activations Density 0.029%

    No Known Activations