© 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. 87852
    Prev
    Next
    INDEX
    Explanations

    describes entities and concepts

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

    romanzo, mosaic, step, supports

    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
     সত্যি
    0.52
    फारिश
    0.50
    liability
    0.48
    ROY
    0.47
    .$-
    0.47
    RENT
    0.45
    鎳
    0.45
     Choisissez
    0.45
    .~
    0.44
     oben
    0.44
    POSITIVE LOGITS
    emor
    0.49
    ané
    0.48
    一组
    0.47
     blackout
    0.46
    gani
    0.45
    gana
    0.42
    uação
    0.42
     monop
    0.42
    નાર
    0.41
     pathologists
    0.41
    Activations Density 0.000%

    No Known Activations