© 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. 198557
    Prev
    Next
    INDEX
    Explanations

    free to generate

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

    fishing, reverse, Meta, path

    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
    Not in Any Lists

    No Comments

    Negative Logits
     k
    0.47
     AFP
    0.47
    terror
    0.45
     ك
    0.44
     keinen
    0.44
     offen
    0.44
     reincarn
    0.43
     authorities
    0.43
     armored
    0.43
    issimo
    0.43
    POSITIVE LOGITS
    釣り
    0.56
    داری
    0.55
    жига
    0.55
    endidikan
    0.52
    юнча
    0.52
    魚
    0.52
     рациона
    0.51
    ૂર્ણ
    0.48
    🎣
    0.47
     ман
    0.47
    Activations Density 0.000%

    No Known Activations