© 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. 93438
    Prev
    Next
    INDEX
    Explanations

    struct definitions

    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
     buckle
    -0.78
     premio
    -0.73
     barras
    -0.72
     ella
    -0.72
     récomp
    -0.70
     Rooms
    -0.69
     темпера
    -0.69
     sample
    -0.69
     outbreak
    -0.68
    mpel
    -0.68
    POSITIVE LOGITS
    DRO
    0.74
     跳
    0.71
     BIL
    0.66
     Dro
    0.65
    bama
    0.65
     granny
    0.65
     Rishi
    0.64
     fats
    0.64
    клар
    0.63
    BIL
    0.63
    Activations Density 0.049%

    No Known Activations