© 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. 144478
    Prev
    Next
    INDEX
    Explanations

    aviation and names

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

    bits and values

    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
    の
    0.49
    ের
    0.48
    的
    0.46
    ₴
    0.45
    н
    0.45
    ą
    0.44
    ی
    0.44
    ın
    0.44
    ‏‏
    0.43
    [,]
    0.42
    POSITIVE LOGITS
    腑
    0.47
     inici
    0.46
     clarification
    0.43
     zacz
    0.43
     möjlig
    0.43
     exploration
    0.43
     clarify
    0.43
    pilot
    0.43
     arbeid
    0.42
    naval
    0.42
    Activations Density 0.000%

    No Known Activations