© 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. 227503
    Prev
    Next
    INDEX
    Explanations

    producedwebsitesatisfywellsystem

    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
    šn
    0.53
     زیر
    0.44
    FRI
    0.43
    ن
    0.43
    ون
    0.43
     পার
    0.43
    Soup
    0.42
    RADI
    0.42
    지
    0.41
    FAMILY
    0.40
    POSITIVE LOGITS
    requestCode
    0.47
     MCQ
    0.47
     furthermore
    0.46
     Kathy
    0.46
     flagpole
    0.46
     Firestore
    0.45
     vzděl
    0.45
     Jaaye
    0.45
     flag
    0.44
    แปล
    0.44
    Activations Density 0.001%

    No Known Activations