© 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. 2829
    Prev
    Next
    INDEX
    Explanations

    Principal Meridian and Range

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

    calculation digits

    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
    朗普
    0.43
     citoyens
    0.43
     wład
    0.41
    民众
    0.41
     podían
    0.41
    操作系统
    0.40
    愔
    0.40
     البيانات
    0.40
    赛事
    0.39
    约翰
    0.39
    POSITIVE LOGITS
    and
    0.54
    the
    0.46
    two
    0.42
    but
    0.42
    ll
    0.42
     and
    0.41
    0.41
    um
    0.41
    in
    0.41
     approximately
    0.40
    Activations Density 0.073%

    No Known Activations