© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146004
    Prev
    Next
    INDEX
    Explanations

    a file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    フォロー
    0.73
     पुन्हा
    0.72
     tüm
    0.70
    équipe
    0.67
    替
    0.67
    なくても
    0.67
     Facilit
    0.66
    Ent
    0.66
     अधी
    0.66
    店
    0.65
    POSITIVE LOGITS
     deep
    0.71
     software
    0.67
    γρα
    0.66
     deeply
    0.66
     tall
    0.66
     ```
    0.64
     sqlalchemy
    0.63
     online
    0.62
     informations
    0.61
    谔
    0.61
    Activations Density 0.004%

    No Known Activations