© 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. 31944
    Prev
    Next
    INDEX
    Explanations

    dimensional image

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

    3d models and dimensional plots

    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
    ،
    0.68
    、
    0.47
    اص
    0.47
    वर्ग
    0.46
     بزر
    0.46
    degenerative
    0.46
    ecd
    0.45
    8
    0.45
    جان
    0.45
     (,
    0.45
    POSITIVE LOGITS
     dimensional
    0.68
    立体
    0.66
     Dimensional
    0.63
    Dimension
    0.61
     geometría
    0.59
     dimensión
    0.59
    zyła
    0.57
    dimensional
    0.57
    \
    0.57
     dimension
    0.55
    Activations Density 0.023%

    No Known Activations