© 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. 175306
    Prev
    Next
    INDEX
    Explanations

    multi-language texts

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

    brutalism, manuals, pressure

    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
     [
    0.54
     I
    0.50
     scene
    0.50
     D
    0.48
     B
    0.47
     as
    0.47
    ened
    0.47
     W
    0.46
    .
    0.46
     Le
    0.46
    POSITIVE LOGITS
    อนไลน์
    0.57
    മൂഹ
    0.55
    鸿
    0.55
    ுகள்
    0.54
    ມັນ
    0.54
    вере
    0.53
    档案馆
    0.53
    വൃത്തി
    0.53
    Mình
    0.52
    ദേശ
    0.52
    Activations Density 0.000%

    No Known Activations