© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12306
    Prev
    Next
    INDEX
    Explanations

    LLaMA, heme, RMSE

    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
    Negative Logits
    اً
    3.51
     estés
    2.68
    uminate
    2.66
    scht
    2.65
    lerin
    2.65
    $('#
    2.61
    sortie
    2.60
     impair
    2.59
    siz
    2.56
    __,
    2.56
    POSITIVE LOGITS
    शेद
    3.03
    м
    3.03
    ნიშვნელ
    2.97
    ั้ย
    2.92
    fehlung
    2.91
    з
    2.89
    ্ভব
    2.85
    деся
    2.78
    ्युनिकेशन
    2.76
    يش
    2.70
    Activations Density 0.218%

    No Known Activations