© 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. 249980
    Prev
    Next
    INDEX
    Explanations

    availability of

    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
    /
    0.53
     खूप
    0.48
    也不
    0.43
    들이
    0.43
    也不能
    0.42
    氏
    0.40
    ASE
    0.40
     footprint
    0.40
     interested
    0.39
    ティア
    0.39
    POSITIVE LOGITS
    প্তাহ
    0.50
     Ciencia
    0.48
     acumul
    0.48
     يخ
    0.48
     Induction
    0.47
     করতাম
    0.46
    睄
    0.46
     Aufnahme
    0.46
     saddhim
    0.46
    getCql
    0.45
    Activations Density 0.004%

    No Known Activations