© 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. 143493
    Prev
    Next
    INDEX
    Explanations

    businesses and services listed

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

    controlling enhancements, watching games, limiting angular motion

    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
    idone
    0.53
    htmlspecialchars
    0.50
    /(:
    0.49
    IndexArray
    0.49
    hình
    0.48
     glTex
    0.47
    бычно
    0.47
    estomac
    0.47
    isotopes
    0.46
     residues
    0.46
    POSITIVE LOGITS
    aki
    0.46
    AI
    0.44
     prochain
    0.44
     entrenched
    0.44
     nový
    0.44
     नई
    0.43
     nové
    0.43
    🧑
    0.43
     devenu
    0.43
     promote
    0.42
    Activations Density 0.001%

    No Known Activations