© 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. 11882
    Prev
    Next
    INDEX
    Explanations

    given, provided, why

    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
    dichlor
    1.24
     Обычно
    1.24
    
    1.23
    xu
    1.22
     κι
    1.19
    朐
    1.18
    ം
    1.17
    슨
    1.16
    i
    1.16
    יות
    1.16
    POSITIVE LOGITS
     outright
    1.19
    ettivi
    1.17
     formal
    1.05
     getY
    1.05
    MaxLength
    1.03
    цева
    1.02
    ну
    1.02
    etze
    1.02
    athermy
    1.01
     verpflichtet
    1.00
    Activations Density 0.000%

    No Known Activations