© 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. 12267
    Prev
    Next
    INDEX
    Explanations

    transparency: : and explanations

    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
    oto
    2.58
    т
    2.52
    न
    2.50
    am
    2.38
    ри
    2.36
    say
    2.34
    ers
    2.34
    থ
    2.23
    た
    2.20
    та
    2.20
    POSITIVE LOGITS
     nods
    2.81
     faptul
    2.67
    م
    2.59
    Upgradeable
    2.54
    ୬
    2.47
    Iddict
    2.44
     fifo
    2.42
    েয়
    2.38
    Ĭ
    2.34
    िस्थित
    2.34
    Activations Density 0.004%

    No Known Activations