© 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. 116003
    Prev
    Next
    INDEX
    Explanations

    parts of phrases and titles

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

    long stop loss take profit

    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
    મના
    0.46
    ించ
    0.46
    ぞ
    0.45
    サービス
    0.45
    ဆိုင်
    0.45
    財務
    0.45
    ایک
    0.45
    せい
    0.45
     Scorpion
    0.44
    鏑
    0.44
    POSITIVE LOGITS
    f
    0.50
    r
    0.48
     tiller
    0.46
    st
    0.45
     paternal
    0.45
     родо
    0.44
    ram
    0.43
     sebagainya
    0.43
    к
    0.43
     administrat
    0.42
    Activations Density 0.001%

    No Known Activations