© 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. 112992
    Prev
    Next
    INDEX
    Explanations

    industry analysis

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

    initialize code structures

    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
    س
    0.59
    اس
    0.52
    م
    0.49
    ج
    0.48
    toISO
    0.48
    ول
    0.48
    د
    0.47
    湖
    0.46
    াট
    0.46
    حص
    0.46
    POSITIVE LOGITS
    bewegung
    0.55
     configur
    0.49
    ộng
    0.49
     आयोजित
    0.46
    つなが
    0.46
     באמצעות
    0.45
    zące
    0.45
    entes
    0.44
    テー
    0.44
     त्याच्या
    0.44
    Activations Density 0.001%

    No Known Activations