© 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. 118520
    Prev
    Next
    INDEX
    Explanations

    Classic or categories

    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
    Janet
    -0.85
    儉
    -0.84
     COIN
    -0.82
     Janet
    -0.79
     mower
    -0.76
    ropra
    -0.75
     orde
    -0.75
    medaille
    -0.74
     PON
    -0.74
    compens
    -0.74
    POSITIVE LOGITS
     Classic
    0.98
     ciudades
    0.86
    Classic
    0.85
     classic
    0.84
     mềm
    0.84
    classic
    0.83
    經典
    0.77
     early
    0.74
     cuadrados
    0.74
     класси
    0.73
    Activations Density 0.028%

    No Known Activations