© 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. 118035
    Prev
    Next
    INDEX
    Explanations

    classroom teachers

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

    strength and character

    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
     இத
    0.49
     mathematically
    0.48
     obviamente
    0.48
     pelanggan
    0.47
    }',
    0.46
     uitge
    0.46
     ingeniería
    0.46
    engineering
    0.44
    NESDAY
    0.44
     computationally
    0.44
    POSITIVE LOGITS
    겁
    0.54
     കാലാവ
    0.46
     Pension
    0.44
     Conditioner
    0.44
     Actress
    0.44
     Wolver
    0.43
    лук
    0.43
    àn
    0.42
    ર્
    0.42
    ="../../../../
    0.42
    Activations Density 0.000%

    No Known Activations