© 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. 22-GEMMASCOPE-2-RES-262K
    7. 11605
    Prev
    Next
    INDEX
    Explanations

    punctuation and connectors

    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_22_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
    이
    1.05
     overwrite
    1.01
    sed
    1.01
    sst
    0.98
     interruption
    0.96
     passé
    0.95
    続く
    0.95
     allure
    0.94
    লেট
    0.93
     immediatamente
    0.93
    POSITIVE LOGITS
    ू
    1.18
    तोड़
    1.15
    ског
    1.13
    nection
    1.11
     πως
    1.11
    ႇ
    1.11
     Persia
    1.11
     Nate
    1.09
     спорттук
    1.09
    BTW
    1.09
    Activations Density 0.000%

    No Known Activations