© 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. 99721
    Prev
    Next
    INDEX
    Explanations

    phrases like "High Value" or "clicked on"

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

    specific concepts and categories

    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
     እንቅ
    0.49
    ниці
    0.47
    нува
    0.46
    굼
    0.46
     konie
    0.46
    關
    0.45
    ಣಿ
    0.45
    ූර්
    0.44
    ይታ
    0.44
    smoothing
    0.43
    POSITIVE LOGITS
     komplett
    0.50
     lainnya
    0.49
     अन्य
    0.48
     informativa
    0.47
     explicando
    0.47
    .".
    0.47
     eller
    0.46
    }
    0.46
     आदिवासी
    0.46
    ).
    0.46
    Activations Density 0.001%

    No Known Activations