© 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. 37700
    Prev
    Next
    INDEX
    Explanations

    region masters study

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

    inherited from

    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
     Parkinson
    0.50
    鐏
    0.50
    ృ
    0.45
     minuten
    0.43
    ర్
    0.43
     बुद्ध
    0.43
     Preset
    0.43
    ంప
    0.42
    ન
    0.42
    лини
    0.41
    POSITIVE LOGITS
    ATIVE
    0.52
     ancestors
    0.45
     invasive
    0.45
     सुर
    0.44
     الداخلية
    0.44
     بہت
    0.44
     অভ্যন্তরীণ
    0.44
     anthropologist
    0.42
    '`--'`--
    0.42
     coastal
    0.42
    Activations Density 0.000%

    No Known Activations