© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57770
    Prev
    Next
    INDEX
    Explanations

    week long, first black

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and vital

    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
    Woh
    0.59
    توان
    0.51
     Technologien
    0.50
    ORES
    0.48
    夏
    0.47
    移動
    0.47
    系
    0.46
    São
    0.46
    Gt
    0.45
    ब्राह
    0.45
    POSITIVE LOGITS
     ionization
    0.52
     மாறி
    0.52
     पू
    0.50
     pull
    0.49
     대
    0.49
     segnal
    0.48
     পরিবর্তন
    0.47
     matchups
    0.47
     variabili
    0.47
    lier
    0.46
    Activations Density 0.000%

    No Known Activations