© 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. 79057
    Prev
    Next
    INDEX
    Explanations

    Permission given, free to copy

    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
     phénomènes
    -0.73
     william
    -0.73
    shed
    -0.72
    ıntı
    -0.69
    ㄊ
    -0.67
     fof
    -0.67
     MACH
    -0.66
    Dens
    -0.65
    Enemy
    -0.65
    囱
    -0.64
    POSITIVE LOGITS
    それとも
    0.79
     obten
    0.66
    řed
    0.66
     gái
    0.66
     Land
    0.63
    偏移
    0.63
    rand
    0.63
     Library
    0.62
    Library
    0.61
    }}]{
    0.61
    Activations Density 0.070%

    No Known Activations