© 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. 208257
    Prev
    Next
    INDEX
    Explanations

    automatic formatting

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

    punctuation and punctuation

    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
    bücher
    0.48
    Magnet
    0.46
    DepartTime
    0.46
    Potato
    0.45
     Automobiles
    0.45
    ној
    0.44
    Obes
    0.44
    🍟
    0.44
    Then
    0.44
     šport
    0.44
    POSITIVE LOGITS
    aligned
    0.53
    ید
    0.52
    فیر
    0.50
    पा
    0.48
    esque
    0.45
     برگزاری
    0.45
    عی
    0.45
    षेक
    0.45
     मौजूदा
    0.44
    मूल
    0.44
    Activations Density 0.001%

    No Known Activations