© 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. 68292
    Prev
    Next
    INDEX
    Explanations

    everyday use

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

    most dangerous cause or loss

    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
    棫
    0.51
    ЕМ
    0.45
    واق
    0.45
    Estamos
    0.44
    勎
    0.44
     想
    0.44
    Ꮢ
    0.44
    Ва
    0.43
    럏
    0.43
    ква
    0.43
    POSITIVE LOGITS
     out
    0.50
    out
    0.49
    _{
    0.46
     outta
    0.46
     हाइट
    0.43
     which
    0.43
    ogen
    0.43
     dearth
    0.43
    ong
    0.42
     S
    0.42
    Activations Density 0.000%

    No Known Activations