© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 31002
    Prev
    Next
    INDEX
    Explanations

    aphantasia or U-235 / needlefelting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فاذا
    0.46
     Fórmula
    0.43
     использованием
    0.43
     algorit
    0.43
     السي
    0.42
     desviación
    0.42
     recuperação
    0.42
    賜
    0.40
     aproveitar
    0.40
     misura
    0.40
    POSITIVE LOGITS
    nobody
    0.54
    uin
    0.50
    expensive
    0.50
    mid
    0.49
    exit
    0.48
    scenes
    0.48
     scenes
    0.47
    conflict
    0.47
    expense
    0.47
    expl
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.