© 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. 221013
    Prev
    Next
    INDEX
    Explanations

    such apparatus or content

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

    handle many languages

    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
    合理的
    0.50
    }$.)
    0.48
     muod
    0.46
     mennes
    0.44
    -'].
    0.44
    rául
    0.43
     naquele
    0.43
    齡
    0.43
    赢
    0.42
     մ
    0.42
    POSITIVE LOGITS
     reprise
    0.51
    or
    0.50
     dialogue
    0.47
     کند
    0.46
     fiancé
    0.46
     shooting
    0.45
     repeat
    0.45
    phan
    0.45
     dialog
    0.45
    alach
    0.45
    Activations Density 0.001%

    No Known Activations