© 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. 182605
    Prev
    Next
    INDEX
    Explanations

    two organizations

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

    specific breed

    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
     avsl
    0.48
    ดับ
    0.47
    ডেল
    0.44
    ريبا
    0.44
    ccia
    0.44
    ቬ
    0.43
     merhabalar
    0.42
     では
    0.42
    ىز
    0.42
     thoracique
    0.42
    POSITIVE LOGITS
    ánicas
    0.49
    日本
    0.48
    至于
    0.47
    不少
    0.47
     getters
    0.47
    로
    0.46
     legible
    0.46
    일본
    0.46
    一般的
    0.45
    인
    0.45
    Activations Density 0.000%

    No Known Activations