© 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. 109214
    Prev
    Next
    INDEX
    Explanations

    post followed by date or event

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

    query would return

    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
    🍽
    0.45
    钓
    0.44
    :
    0.44
     Fores
    0.43
     Tasting
    0.41
    र्मा
    0.40
    on
    0.40
    ORES
    0.40
    濡
    0.39
    𝕠
    0.39
    POSITIVE LOGITS
     agonizing
    0.47
    vature
    0.46
     الشكل
    0.45
    seleccion
    0.44
    computation
    0.43
    calculate
    0.43
     அல்
    0.42
    wrapped
    0.42
     ஆராய்ச்சி
    0.41
     பிரபலமான
    0.41
    Activations Density 0.000%

    No Known Activations