© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9922
    Prev
    Next
    INDEX
    Explanations

    word claim

    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
    न
    3.57
    ように
    3.54
    ה
    3.45
    ্য
    3.37
    ment
    2.87
    ്യ
    2.84
    पटा
    2.80
    ی
    2.72
     blink
    2.60
    ا
    2.60
    POSITIVE LOGITS
    el
    3.97
    र
    3.25
    ే
    3.09
    লা
    3.01
    و
    2.66
    𝘵
    2.65
    ו
    2.56
    𝘶
    2.44
    रन
    2.42
    ность
    2.42
    Activations Density 0.065%

    No Known Activations