© 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. 247684
    Prev
    Next
    INDEX
    Explanations

    balance, minutes, games

    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
    త్రిక
    0.54
     Reuters
    0.48
    Reuters
    0.46
    Nigeria
    0.46
    Philips
    0.45
    örungen
    0.45
    सायनिक
    0.44
    🇬
    0.43
    म्र
    0.43
    Bengal
    0.43
    POSITIVE LOGITS
     contro
    0.47
     de
    0.45
     configure
    0.44
     緊急
    0.44
     goalt
    0.43
     probe
    0.43
    ונ
    0.43
    駕駛
    0.43
     מע
    0.42
     JV
    0.42
    Activations Density 0.000%

    No Known Activations