© 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. 182943
    Prev
    Next
    INDEX
    Explanations

    contact you

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

    functionality and context

    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
    }|^{
    0.47
     quelcon
    0.47
     வேகமாக
    0.47
     বক্তব
    0.46
    itattu
    0.45
     irrég
    0.45
    ၸ
    0.44
     wichtige
    0.44
    NewLine
    0.43
     숫
    0.42
    POSITIVE LOGITS
     ALWAYS
    0.52
     preparation
    0.46
    ALWAYS
    0.45
     planter
    0.43
     o
    0.43
     about
    0.42
     EN
    0.42
    리스
    0.42
    常に
    0.42
     always
    0.42
    Activations Density 0.000%

    No Known Activations