© 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-16K
    7. 12378
    Prev
    Next
    INDEX
    Explanations

    commented lines and directives

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

    Get, Check, Trans, Display, Print

    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_16k_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
    我
    0.51
    逻辑
    0.50
     */
    0.49
     utiliser
    0.49
     可以
    0.49
     Aufgaben
    0.48
    ↵
    0.47
    我们可以
    0.47
    可以
    0.47
     احنا
    0.47
    POSITIVE LOGITS
    is
    0.49
    on
    0.44
    itriangular
    0.43
    isTrack
    0.43
     getTime
    0.42
    (':')[
    0.42
    ivne
    0.42
    ix
    0.41
     râ
    0.40
    ravel
    0.40
    Activations Density 0.001%

    No Known Activations