© 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. 243951
    Prev
    Next
    INDEX
    Explanations

    roles, economics, students, sauce, access, study

    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
    .\\
    0.44
    Time
    0.43
    riy
    0.43
    udence
    0.43
    ។
    0.43
     её
    0.43
    }
    0.42
    .​
    0.42
    .(
    0.42
    ardan
    0.42
    POSITIVE LOGITS
     equips
    0.45
    styles
    0.45
    addSubview
    0.45
     पार्किंग
    0.45
    원
    0.45
    ెక్టర్
    0.45
    ন
    0.44
    كتوبر
    0.44
     marinas
    0.44
    েনার
    0.44
    Activations Density 0.000%

    No Known Activations