© 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. 11124
    Prev
    Next
    INDEX
    Explanations

    specific classifications

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

    8-bit, 16-bit, INT8

    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
    වන
    0.49
    udsman
    0.48
    मीत
    0.46
    억원
    0.45
    калә
    0.44
     encouraged
    0.42
    ากหลาย
    0.42
    츈
    0.41
    ѐ
    0.41
    ve
    0.40
    POSITIVE LOGITS
     invece
    0.49
     tzw
    0.48
     sogenannte
    0.48
    👺
    0.48
     reincarnation
    0.47
    😈
    0.47
     pseudo
    0.47
     جسم
    0.47
     inferior
    0.46
     transmutation
    0.46
    Activations Density 0.000%

    No Known Activations