© 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. 207035
    Prev
    Next
    INDEX
    Explanations

    For those release

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

    Internal visibility and coverage

    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
     legislatures
    0.48
    附
    0.45
    直線
    0.45
    나
    0.45
    杼
    0.45
    intensité
    0.44
    を経
    0.44
     laws
    0.43
    봇
    0.43
    機器
    0.43
    POSITIVE LOGITS
     Supports
    0.49
     Sophie
    0.48
     Squash
    0.47
     Swim
    0.47
     Supporters
    0.46
     Anyways
    0.45
     Fairbanks
    0.44
     Toen
    0.44
     समीप
    0.44
     adım
    0.43
    Activations Density 0.000%

    No Known Activations