© 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. 79082
    Prev
    Next
    INDEX
    Explanations

    regex`^\s`

    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
    拗
    -0.89
    あとは
    -0.81
     again
    -0.77
    ！(
    -0.76
     this
    -0.75
    ？（
    -0.75
     geblieben
    -0.74
    करण
    -0.74
     garansi
    -0.74
     Helfer
    -0.73
    POSITIVE LOGITS
    ^\
    1.13
    ^
    1.03
     a
    0.93
    ০
    0.88
    gió
    0.85
    timmung
    0.84
    이트
    0.82
    𝑎
    0.82
     uranium
    0.81
    Uruguay
    0.80
    Activations Density 0.019%

    No Known Activations