© 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. 251582
    Prev
    Next
    INDEX
    Explanations

    how to choose window treatments

    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
    *)
    0.48
     rights
    0.43
     depreci
    0.42
     coales
    0.42
     зо
    0.41
    $?
    0.41
    ')
    0.41
     occup
    0.40
     diagnostic
    0.40
     $(*
    0.40
    POSITIVE LOGITS
    लाब
    0.47
     یہودی
    0.47
    բ
    0.47
    H
    0.46
     گفته
    0.46
     descrito
    0.46
    मॉडल
    0.45
     maravilloso
    0.45
    بانی
    0.45
    TempValue
    0.45
    Activations Density 0.003%

    No Known Activations