© 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. 162281
    Prev
    Next
    INDEX
    Explanations

    lists or specific sequences

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

    broadening

    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
     upgrading
    0.54
    RuntimeException
    0.53
     vacations
    0.52
     cysts
    0.52
    вают
    0.50
    蕖
    0.49
     granddaughters
    0.48
     குழந்தைகள்
    0.47
     গেরিলারা
    0.47
     degradation
    0.46
    POSITIVE LOGITS
    。
    0.52
     、
    0.45
     。
    0.45
    ström
    0.44
    八
    0.44
    êu
    0.43
    Ĕ
    0.41
     EP
    0.41
    眉
    0.41
    这时
    0.40
    Activations Density 0.000%

    No Known Activations