© 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. 22-GEMMASCOPE-RES-131K
    7. 26729
    Prev
    Next
    INDEX
    Explanations

    following HTML/code/technical terms

    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_22/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
     garda
    -0.98
    i
    -0.87
     casein
    -0.84
     stea
    -0.84
    存知
    -0.84
    vait
    -0.83
     stic
    -0.82
     marinas
    -0.82
    а
    -0.81
    zação
    -0.80
    POSITIVE LOGITS
     péro
    1.03
     jsonObj
    0.98
    føre
    0.97
    brasil
    0.95
    </h4>
    0.93
    …~
    0.92
     setMessage
    0.90
     signUp
    0.88
     paſſ
    0.87
     indien
    0.86
    Activations Density 0.092%

    No Known Activations