© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9486
    Prev
    Next
    INDEX
    Explanations

    import and important

    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
     behalf
    1.19
    k
    1.14
     جزء
    1.08
     এছাড়া
    1.08
    skiy
    1.07
     днем
    1.07
    )}{\
    1.04
    kowski
    1.03
    eus
    1.03
     आलोक
    1.01
    POSITIVE LOGITS
     operativa
    1.35
    an
    1.29
     rada
    1.20
     vede
    1.20
    issimi
    1.20
    ities
    1.17
    就是在
    1.16
     absch
    1.14
     lieber
    1.13
    可
    1.13
    Activations Density 0.000%

    No Known Activations