© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11287
    Prev
    Next
    INDEX
    Explanations

    to inspire goals

    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_9_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
     nouvel
    1.34
     понятия
    1.30
    ırım
    1.22
    পাশ
    1.19
     хотели
    1.18
    詎
    1.18
    вало
    1.18
     preuve
    1.16
     срока
    1.13
    ifiant
    1.12
    POSITIVE LOGITS
    ك
    1.43
    d
    1.37
    я
    1.37
     Punj
    1.27
    ف
    1.20
    j
    1.18
    ح
    1.17
    Nk
    1.17
    k
    1.17
    tact
    1.16
    Activations Density 0.000%

    No Known Activations