© 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. 73826
    Prev
    Next
    INDEX
    Explanations

    Few athletes

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

    specific content descriptions

    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
    in
    0.48
    seven
    0.47
    0
    0.47
    stamp
    0.46
    named
    0.45
    unknown
    0.43
    at
    0.43
    3
    0.43
    this
    0.41
    drag
    0.41
    POSITIVE LOGITS
     ക്ലാ
    0.47
     руха
    0.46
     RATES
    0.44
     HIIT
    0.44
     classico
    0.44
     ભા
    0.43
     yür
    0.43
     tío
    0.43
     DME
    0.43
     clásico
    0.43
    Activations Density 0.001%

    No Known Activations