© 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. 57212
    Prev
    Next
    INDEX
    Explanations

    current time, character nature

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

    refers to canal or Euclidean norm

    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
    hall
    0.45
    Ｌ
    0.43
    Hall
    0.43
     Hall
    0.40
    HALL
    0.40
    চার
    0.39
    কাঠ
    0.39
    ୫
    0.39
    ेक्षा
    0.39
     Schl
    0.38
    POSITIVE LOGITS
     العمود
    0.46
     מס
    0.43
     zemlji
    0.43
     amply
    0.43
    ypi
    0.42
     簡単
    0.42
     активно
    0.41
     втори
    0.41
     agonizing
    0.41
     avión
    0.40
    Activations Density 0.000%

    No Known Activations