© 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. 206749
    Prev
    Next
    INDEX
    Explanations

    listsitemsbulletsordered lists

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

    Section division

    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
     ישראל
    0.46
     امی
    0.41
     образования
    0.40
    SRPI
    0.40
    сько
    0.39
    Primero
    0.39
     যথ
    0.39
    𝚞
    0.39
     クリーム
    0.39
    고자
    0.38
    POSITIVE LOGITS
    ent
    0.46
     or
    0.44
    WO
    0.44
    /
    0.43
    ode
    0.43
     SM
    0.42
    wo
    0.42
     Theme
    0.42
     Async
    0.42
    ond
    0.41
    Activations Density 0.003%

    No Known Activations