© 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. 89266
    Prev
    Next
    INDEX
    Explanations

    Remove these

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

    based on

    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
     بالضبط
    0.47
    MM
    0.47
     INCLUDING
    0.44
    బ
    0.41
    UR
    0.41
     commuting
    0.40
    packaging
    0.40
     wavelengths
    0.40
     EXACT
    0.40
     दायर
    0.39
    POSITIVE LOGITS
    ToServer
    0.49
    uei
    0.48
    iseum
    0.46
    塁
    0.44
     Tous
    0.44
    igues
    0.43
    setzen
    0.43
     setToDefault
    0.42
    ཕ
    0.42
    이드
    0.42
    Activations Density 0.000%

    No Known Activations