© 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. 77643
    Prev
    Next
    INDEX
    Explanations

    file formats like xls

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

    incidence of, tibiofibular joint

    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
     পারস্প
    0.52
    ('{
    0.51
    illé
    0.50
    িয়েত
    0.50
    ቖ
    0.48
    ៨
    0.48
    lius
    0.47
    schaft
    0.47
    )}$,
    0.46
    ]}$.
    0.46
    POSITIVE LOGITS
     한번
    0.55
     Temos
    0.52
     CREAM
    0.49
     marshmallows
    0.48
     LESS
    0.47
     ITAL
    0.47
     Tenemos
    0.46
     accl
    0.45
     echi
    0.45
     planis
    0.44
    Activations Density 0.000%

    No Known Activations