© 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. 163782
    Prev
    Next
    INDEX
    Explanations

    descriptions of states or outcomes

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

    potential nuance and outcomes

    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
     incredibly
    0.57
    ূল
    0.52
     increíble
    0.46
    蛊
    0.44
    ্ত্র
    0.43
    িলাম
    0.42
     unglaublich
    0.41
    럼
    0.41
     Runde
    0.41
     Elim
    0.41
    POSITIVE LOGITS
    andra
    0.61
    andy
    0.49
     maintenir
    0.49
     люби
    0.48
     συνεργ
    0.46
    婍
    0.46
     銀
    0.45
    lients
    0.45
    formen
    0.45
    imper
    0.45
    Activations Density 0.001%

    No Known Activations