© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76656
    Prev
    Next
    INDEX
    Explanations

    C++ include statements

    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
    headless
    -0.66
     coefficient
    -0.66
     lavor
    -0.63
    コの
    -0.63
     Bentham
    -0.62
    阵
    -0.62
     Armstrong
    -0.61
    部長
    -0.61
     Colorado
    -0.60
    colorado
    -0.60
    POSITIVE LOGITS
     permitiendo
    0.66
    に行く
    0.65
    Lottery
    0.65
     Маль
    0.65
    angleright
    0.65
    förmig
    0.64
     Gasoline
    0.63
    يج
    0.63
    ETER
    0.63
    μα
    0.63
    Activations Density 0.085%

    No Known Activations