© 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. 12276
    Prev
    Next
    INDEX
    Explanations

    quality time together

    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
    eses
    1.19
    zcz
    1.13
    itto
    1.12
     presentada
    1.12
     Brexit
    1.12
     নিয়েছে
    1.10
     ModInt
    1.09
    osos
    1.08
    盹
    1.08
    হাম্মদ
    1.06
    POSITIVE LOGITS
     zicht
    1.16
    ngth
    1.11
     ㅣ
    1.11
     Aki
    1.11
     ikan
    1.10
    /[\
    1.10
    flatten
    1.09
    যাপন
    1.08
    LING
    1.08
     fär
    1.07
    Activations Density 0.001%

    No Known Activations