© 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. 12334
    Prev
    Next
    INDEX
    Explanations

    problems, specific things, thoughts

    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
    decrement
    1.19
    Est
    1.06
    rone
    1.04
     Minimalism
    0.99
     spurs
    0.99
    ாலி
    0.99
     excuse
    0.99
    ಕ
    0.98
    াক
    0.97
     installment
    0.97
    POSITIVE LOGITS
    ([[
    1.45
    ชาว
    1.41
     tämän
    1.40
    elor
    1.34
     trolling
    1.32
    elda
    1.31
    
    1.28
    অন্য
    1.27
     τρό
    1.27
    unt
    1.27
    Activations Density 0.000%

    No Known Activations