© 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. 225204
    Prev
    Next
    INDEX
    Explanations

    No, not only

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

    JSON, Java, commands

    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
     médecin
    0.55
     ඔහුගේ
    0.52
     fuelwood
    0.52
     പൂർ
    0.51
    apolitan
    0.51
     Ñ
    0.51
     සිය
    0.50
     Govt
    0.49
     BOA
    0.49
     ier
    0.49
    POSITIVE LOGITS
    0
    0.55
    喎
    0.52
    OutputPath
    0.51
    却
    0.48
    ROSS
    0.46
    די
    0.46
    ξε
    0.46
    BUFFER
    0.46
    եց
    0.46
    ב
    0.46
    Activations Density 0.001%

    No Known Activations