© 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. 162457
    Prev
    Next
    INDEX
    Explanations

    procedures unless

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

    ad hoc network

    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
     sucesión
    0.46
    dicts
    0.44
     carène
    0.44
    hun
    0.44
     publiée
    0.44
    hane
    0.43
    ╅
    0.43
     मात्र
    0.43
     thighs
    0.43
    राइ
    0.43
    POSITIVE LOGITS
    에는
    0.49
     Sommers
    0.46
    WAT
    0.45
    Wat
    0.44
     Centennial
    0.43
    мпа
    0.42
     Boulevard
    0.42
    <0x15>
    0.41
     taped
    0.40
    getElementById
    0.40
    Activations Density 0.000%

    No Known Activations