© 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. 229625
    Prev
    Next
    INDEX
    Explanations

    delivery possible on updates

    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
    ]){
    0.50
    รร
    0.46
    pathetic
    0.46
    療法
    0.45
    ∂</
    0.45
    ]_
    0.44
    \}-
    0.44
    都會
    0.44
    ra
    0.43
    ະ
    0.42
    POSITIVE LOGITS
     handels
    0.47
     মিথ
    0.46
     좋아
    0.45
     ২০১০
    0.44
    ита
    0.44
     передба
    0.42
     situations
    0.41
    ität
    0.41
     процес
    0.41
     Kato
    0.40
    Activations Density 0.000%

    No Known Activations