© 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. 49577
    Prev
    Next
    INDEX
    Explanations

    into, offer, as, to, up, this, body

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

    gemmae cups or voltage

    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
     mó
    0.45
    ﾌ
    0.45
    Flame
    0.44
    HAS
    0.44
    Platinum
    0.43
    াগর
    0.43
    Lambda
    0.42
    Strategies
    0.42
    Caribbean
    0.42
     ይህ
    0.42
    POSITIVE LOGITS
     remarks
    0.48
    ز
    0.46
     لحظ
    0.45
     爱
    0.44
     absences
    0.44
     زخ
    0.44
    ли
    0.43
     ع
    0.42
     glimpses
    0.42
    ع
    0.42
    Activations Density 0.000%

    No Known Activations