© 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. 3232
    Prev
    Next
    INDEX
    Explanations

    names with "sel" or "shell" sounds

    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
     Bogotá
    -0.73
     undergrad
    -0.73
    ξε
    -0.73
    Зак
    -0.72
     bide
    -0.71
     huma
    -0.71
     Minis
    -0.70
     adaptación
    -0.70
     cornstarch
    -0.70
     surpassing
    -0.69
    POSITIVE LOGITS
    nuts
    0.85
     Dick
    0.79
     TON
    0.78
    errated
    0.76
     missile
    0.75
    Dick
    0.74
     propias
    0.74
    rams
    0.73
     propios
    0.72
    TOF
    0.71
    Activations Density 0.037%

    No Known Activations