© 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. 32531
    Prev
    Next
    INDEX
    Explanations

    phone numbers or codes

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

    codes or identifiers

    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
    ות
    0.65
    ן
    0.59
    ርግ
    0.57
    し
    0.57
    لوب
    0.55
    个
    0.55
    عة
    0.55
    ותו
    0.55
    ש
    0.55
    მე
    0.54
    POSITIVE LOGITS
    addie
    0.47
    <0x80>
    0.47
     Feld
    0.46
     Delphi
    0.45
     Vic
    0.45
     Mafia
    0.45
     KR
    0.44
     Joo
    0.44
     Sheriff
    0.44
     KPK
    0.44
    Activations Density 0.043%

    No Known Activations