© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80172
    Prev
    Next
    INDEX
    Explanations

    blaming and punish approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     这里
    0.57
     русской
    0.49
     其他
    0.48
    MathMarks
    0.48
     விழுப்பு
    0.47
     современной
    0.47
    engesellschaft
    0.47
    锗
    0.47
     刘
    0.47
    éns
    0.46
    POSITIVE LOGITS
     pest
    0.47
     impover
    0.46
     famine
    0.45
     pier
    0.45
     historian
    0.44
     kind
    0.44
     tired
    0.44
     seterusnya
    0.43
     grassroots
    0.42
     jau
    0.42
    Activations Density 0.000%

    No Known Activations