© 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. 153316
    Prev
    Next
    INDEX
    Explanations

    party

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

    company descriptions and scores

    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
     Höhe
    0.50
    يّ
    0.50
    வனின்
    0.46
     Height
    0.45
     ল
    0.45
     converges
    0.44
     Heights
    0.44
    ്
    0.44
    ي
    0.44
     werden
    0.43
    POSITIVE LOGITS
     לר
    0.49
     снять
    0.49
    tsioon
    0.47
     없고
    0.46
     জামাল
    0.46
    胺
    0.46
     gaskets
    0.45
    нкт
    0.45
     barco
    0.45
    𝙳
    0.45
    Activations Density 0.001%

    No Known Activations