© 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. 106753
    Prev
    Next
    INDEX
    Explanations

    code signature match

    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
    şen
    -0.73
    hy
    -0.72
    Inconvénients
    -0.69
    dts
    -0.68
    мыш
    -0.67
    let
    -0.66
    userdata
    -0.66
     about
    -0.65
    しき
    -0.65
    ou
    -0.64
    POSITIVE LOGITS
    Bras
    0.74
     Newsroom
    0.70
     CNA
    0.69
     каждо
    0.68
    Moses
    0.67
     Mecca
    0.67
    maka
    0.67
    erencias
    0.67
     Bras
    0.66
    vesi
    0.66
    Activations Density 0.056%

    No Known Activations