© 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. 227319
    Prev
    Next
    INDEX
    Explanations

    year range set

    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
     ƙ
    0.52
     aş
    0.50
     rejuven
    0.49
     tân
    0.47
    şı
    0.47
     gusta
    0.47
     பயன்படுகிறது
    0.46
     Tân
    0.46
     voltar
    0.46
     grime
    0.46
    POSITIVE LOGITS
    迦
    0.52
    ถา
    0.48
    เด
    0.47
    流畅
    0.44
    휙
    0.44
    MER
    0.43
    斯特
    0.43
    쁠
    0.43
    пут
    0.42
    越大
    0.42
    Activations Density 0.000%

    No Known Activations