© 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. 152846
    Prev
    Next
    INDEX
    Explanations

    Google AdWords

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

    data formatting for LLMs

    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
    差
    0.47
     راستہ
    0.43
    휙
    0.43
     finer
    0.42
    💓
    0.42
    $\{
    0.42
    욜
    0.42
    avance
    0.41
    わけ
    0.40
    祥
    0.40
    POSITIVE LOGITS
    AGER
    0.56
     买
    0.51
    AKER
    0.50
     GARD
    0.50
    ెండు
    0.48
    Dialog
    0.48
     dinners
    0.47
     doctor
    0.47
     households
    0.47
     ಮುಖ್ಯ
    0.47
    Activations Density 0.000%

    No Known Activations