© 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. 8975
    Prev
    Next
    INDEX
    Explanations

    submit an action

    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
    ي
    4.44
    ષ્ટ્ર
    2.69
     busc
    2.66
    客様
    2.65
    不然
    2.64
     rừng
    2.63
    ком
    2.63
    elizmente
    2.58
    াং
    2.58
    خیص
    2.57
    POSITIVE LOGITS
    stva
    3.20
    ियों
    2.99
    ogliere
    2.89
    ם
    2.84
    ্স
    2.82
    ই
    2.80
    nji
    2.77
    "${
    2.77
    ിയി
    2.77
    |\
    2.75
    Activations Density 0.019%

    No Known Activations