© 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. 89794
    Prev
    Next
    INDEX
    Explanations

    know how to use

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

    ratio, coding, differentiable, individual

    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
    h
    0.63
    {
    0.59
    *
    0.50
    aley
    0.50
    ili
    0.49
    gs
    0.47
    ő
    0.47
    ila
    0.47
    <
    0.46
    yn
    0.46
    POSITIVE LOGITS
     ENO
    0.59
     AGRICULTURAL
    0.55
     رياض
    0.53
     сказа
    0.52
     имел
    0.52
     எதிர்க்க
    0.52
     ಬಳಸ
    0.51
     ಸಾಮಾನ್ಯವಾಗಿ
    0.51
     ночью
    0.51
     сказал
    0.50
    Activations Density 0.000%

    No Known Activations