© 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. 193929
    Prev
    Next
    INDEX
    Explanations

    global organizations and science

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

    control, identify, vulnerabilities, skill, fluid

    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
     Sarg
    0.55
    잍
    0.50
     جذر
    0.47
    맇
    0.46
    얄
    0.45
     Saad
    0.43
     spineItem
    0.43
    <unused402>
    0.43
    <unused1894>
    0.42
     叶
    0.42
    POSITIVE LOGITS
    Science
    0.47
    Telecom
    0.47
    Global
    0.46
     নিউজ
    0.46
    रेक्ट
    0.46
     bilen
    0.46
    CDC
    0.45
    ixin
    0.45
     ಕಿ
    0.45
     Теле
    0.44
    Activations Density 0.000%

    No Known Activations