© 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. 8600
    Prev
    Next
    INDEX
    Explanations

    ranking and strategies

    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
    ました
    1.68
    ましたが
    1.61
     заместитель
    1.61
    tolerant
    1.61
    ⓪
    1.58
     fighting
    1.54
     destitute
    1.54
    ㌔
    1.50
    serialize
    1.50
     divalent
    1.49
    POSITIVE LOGITS
    ح
    1.34
    东西
    1.33
     incomple
    1.33
    $\
    1.28
    いますが
    1.26
     anf
    1.25
    حق
    1.22
    <b>
    1.22
    iv
    1.21
    แหน่ง
    1.20
    Activations Density 0.000%

    No Known Activations