© 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. 126566
    Prev
    Next
    INDEX
    Explanations

    reasons, buyers, dates, months

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

    designs, minimizing, mimicking, removable

    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
     profitability
    0.50
     Covington
    0.46
     Upton
    0.45
    эффици
    0.45
     выпущен
    0.42
    淘汰
    0.42
    颇
    0.42
     اخذنا
    0.42
     Zol
    0.42
     Profits
    0.41
    POSITIVE LOGITS
    IZED
    0.46
     スマ
    0.46
    ATES
    0.46
     อย่า
    0.45
    ANCES
    0.45
     把
    0.45
    ruv
    0.45
     immor
    0.45
    unjungi
    0.44
     つ
    0.43
    Activations Density 0.002%

    No Known Activations