© 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. 12307
    Prev
    Next
    INDEX
    Explanations

    code blocks and formatting

    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
     Numerous
    1.81
     Ministério
    1.80
    odas
    1.76
    ra
    1.75
    จัย
    1.71
    ا
    1.68
     Beleza
    1.67
     lysates
    1.66
     oppress
    1.65
    枨
    1.63
    POSITIVE LOGITS
    होस्
    1.36
    ҽ
    1.34
    ke
    1.26
    те
    1.26
     gon
    1.24
    лый
    1.24
    jen
    1.23
     jen
    1.20
    ال
    1.20
    _:
    1.20
    Activations Density 0.000%

    No Known Activations