© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92468
    Prev
    Next
    INDEX
    Explanations

    library cleanup

    np_acts-logits-general · gemini-2.5-flash-lite

    popularity and interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    auj
    0.54
     ਆਪਣੇ
    0.53
    älj
    0.49
     चौराहे
    0.49
    osiery
    0.47
    hattisgarh
    0.47
     कुसुम
    0.47
    嗉
    0.46
    kannten
    0.46
     हौ
    0.46
    POSITIVE LOGITS
    அ
    0.47
     olmadan
    0.46
     დ
    0.46
     experimentos
    0.45
     frecu
    0.44
     diversos
    0.44
     splend
    0.44
    dır
    0.44
     Scud
    0.44
    დან
    0.43
    Activations Density 0.001%

    No Known Activations