© 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. 245433
    Prev
    Next
    INDEX
    Explanations

    customizable specific quality

    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
     किंवा
    0.57
     หรือ
    0.49
     เหมาะ
    0.47
     و
    0.46
     เม
    0.45
    讓你
    0.44
     noma
    0.44
     හෝ
    0.44
     ị
    0.44
    让你
    0.43
    POSITIVE LOGITS
    ABILITY
    0.49
     anderen
    0.46
     отече
    0.45
    죤
    0.44
     других
    0.43
     сосед
    0.42
     собственные
    0.41
     refunded
    0.41
    $:
    0.40
     другим
    0.40
    Activations Density 0.000%

    No Known Activations