© 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. 38800
    Prev
    Next
    INDEX
    Explanations

    it should be fixed

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

    Gemini research family models

    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
    فيف
    0.48
     Kanal
    0.47
     Seç
    0.42
     Nuestra
    0.41
     Wy
    0.41
    簟
    0.41
     Cuenta
    0.40
     Discipl
    0.40
    ผ
    0.40
    بل
    0.40
    POSITIVE LOGITS
     championed
    0.56
     formulated
    0.55
     excreted
    0.51
     effectiveness
    0.49
    laboratory
    0.48
     formulation
    0.47
     importance
    0.46
     amelior
    0.46
    teger
    0.46
     mortality
    0.46
    Activations Density 0.000%

    No Known Activations