© 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. 44287
    Prev
    Next
    INDEX
    Explanations

    straightforward outline

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

    flavorful food

    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
     priming
    0.47
     selectively
    0.46
     textile
    0.45
    将
    0.45
    的关键
    0.44
     trouver
    0.44
    سی
    0.44
     sass
    0.44
     '+':
    0.43
     highlighting
    0.42
    POSITIVE LOGITS
    𝗵
    0.55
    TRAS
    0.53
    IZA
    0.52
    
    0.50
    ˀ
    0.48
    MET
    0.48
     Лон
    0.48
    UNDO
    0.47
     Chaud
    0.47
    ﺤ
    0.46
    Activations Density 0.000%

    No Known Activations