© 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. 12048
    Prev
    Next
    INDEX
    Explanations

    Maven groupId tags

    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
    ه
    3.21
    o
    3.05
    े
    2.90
    هما
    2.75
    ו
    2.74
    quela
    2.74
    oa
    2.64
    一个
    2.61
    ો
    2.57
    ために
    2.51
    POSITIVE LOGITS
    ের
    2.68
    ue
    2.60
    le
    2.60
    ون
    2.52
    śmy
    2.49
    '.$
    2.40
    Enumerable
    2.39
     temprana
    2.38
    ի
    2.38
    ﺍ
    2.33
    Activations Density 0.000%

    No Known Activations