© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2333
    Prev
    Next
    INDEX
    Explanations

    edges, sides, and walls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     as
    1.36
    ə
    0.98
    ;
    0.81
     aliqu
    0.79
    রা
    0.76
     or
    0.74
    q
    0.74
    ;")
    0.72
    นั้น
    0.71
     legado
    0.70
    POSITIVE LOGITS
    om
    1.05
    ot
    1.04
    or
    0.92
    et
    0.91
    एम
    0.88
    iin
    0.88
    0.84
    borders
    0.83
    ución
    0.82
    ehr
    0.82
    Activations Density 0.409%

    No Known Activations