© 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. 64973
    Prev
    Next
    INDEX
    Explanations

    Goblin King, Access Control

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

    but

    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
    坚持
    0.51
    ache
    0.49
    ،
    0.49
    attacking
    0.48
    literal
    0.47
    лій
    0.45
    Literal
    0.44
     prosecuting
    0.44
    ামার
    0.44
    تالي
    0.43
    POSITIVE LOGITS
     OXIDES
    0.53
     ใบ
    0.47
    WD
    0.46
     สน
    0.46
     COSM
    0.46
    หย
    0.46
    ⊡
    0.45
    EL
    0.45
    UND
    0.44
    OVER
    0.44
    Activations Density 0.000%

    No Known Activations