© 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. 203103
    Prev
    Next
    INDEX
    Explanations

    wiring switches

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

    wears dresses

    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
     RAID
    0.48
     dậy
    0.47
     осигурање
    0.45
     Overwatch
    0.43
     Brown
    0.43
     R
    0.43
     Fox
    0.42
     Head
    0.42
     Redding
    0.42
     Rack
    0.42
    POSITIVE LOGITS
    arete
    0.50
    ških
    0.48
    ድ
    0.48
    allar
    0.47
    roben
    0.46
    ㎜
    0.46
    朮
    0.46
    ouv
    0.46
    awie
    0.46
    acjach
    0.46
    Activations Density 0.000%

    No Known Activations