© 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. 9991
    Prev
    Next
    INDEX
    Explanations

    the point is

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

    point and items

    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
    ّ
    0.66
    k
    0.65
    ffect
    0.64
    湇
    0.63
    ри
    0.63
     Haci
    0.62
    gypt
    0.61
    kiej
    0.61
     Πα
    0.60
    gebaut
    0.60
    POSITIVE LOGITS
     points
    1.46
    点的
    1.41
     point
    1.37
     puntos
    1.37
    点
    1.30
    points
    1.29
     punti
    1.28
     نقطه
    1.23
     điểm
    1.21
     Points
    1.17
    Activations Density 0.054%

    No Known Activations