© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93475
    Prev
    Next
    INDEX
    Explanations

    code functions and titles

    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
     المثال
    -0.85
     frases
    -0.84
     whatnot
    -0.83
     đ
    -0.83
    орга
    -0.82
    gués
    -0.80
     vín
    -0.80
     novin
    -0.80
    arnes
    -0.79
     suç
    -0.79
    POSITIVE LOGITS
     void
    0.93
     legging
    0.92
    void
    0.92
    吹き
    0.88
     appreciation
    0.84
     attestation
    0.81
    колеп
    0.81
     EIF
    0.80
     JPM
    0.80
    jacency
    0.79
    Activations Density 0.012%

    No Known Activations