© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148180
    Prev
    Next
    INDEX
    Explanations

    figure out

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

    code comments and file names

    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
    :
    0.63
    u
    0.62
       
    0.56
    ;
    0.55
     af
    0.51
     nasa
    0.50
     storie
    0.50
    1
    0.49
     performances
    0.49
    <h2>
    0.48
    POSITIVE LOGITS
     Bước
    0.53
     Казіно
    0.52
    Butyl
    0.50
    Ꮘ
    0.50
    ಾಗಿತ್ತು
    0.48
    笑了
    0.47
     한다
    0.47
    Pedido
    0.47
    Pherson
    0.46
    뭡
    0.46
    Activations Density 0.000%

    No Known Activations