© 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. 139816
    Prev
    Next
    INDEX
    Explanations

    sailing gloves

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

    states, actions, or qualities

    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
     bigotry
    0.51
    っしゃ
    0.48
     importation
    0.47
    Outline
    0.45
     インド
    0.44
     লাগবে
    0.44
    DATABASE
    0.44
     கை
    0.42
     **,
    0.42
     illiterate
    0.42
    POSITIVE LOGITS
    暂
    0.50
    悠
    0.49
     Ret
    0.47
    甜
    0.47
    空间的
    0.46
     Microscopy
    0.45
    能够
    0.45
    க்கர
    0.45
    宽
    0.45
     been
    0.44
    Activations Density 0.000%

    No Known Activations