© 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. 83722
    Prev
    Next
    INDEX
    Explanations

    old saying learned neighbors tale forcer

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

    handle, designed, battery, trailer, gallon

    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
     desigualdad
    0.49
     coer
    0.46
    狀
    0.46
    antiate
    0.45
    រយៈពេល
    0.44
    vai
    0.44
     trại
    0.43
     உயரம்
    0.43
    認知
    0.43
     священ
    0.42
    POSITIVE LOGITS
    s
    0.70
    ים
    0.47
     Fuß
    0.46
     installation
    0.46
     install
    0.45
    ة
    0.45
    реза
    0.44
     PowerShell
    0.44
     gunmen
    0.43
    libp
    0.43
    Activations Density 0.001%

    No Known Activations