© 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. 53875
    Prev
    Next
    INDEX
    Explanations

    BBC Radio

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

    Key features and capabilities

    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
     CENTRE
    0.48
    pans
    0.47
     kelamin
    0.44
    ια
    0.43
     শুনি
    0.42
    position
    0.42
    自己的
    0.42
    ᱕
    0.41
     consecutive
    0.41
    third
    0.41
    POSITIVE LOGITS
     almu
    0.56
     alcoved
    0.54
     พระเจ้า
    0.49
     isAuthenticated
    0.49
     Bedür
    0.48
     Será
    0.48
     Grec
    0.47
     evoc
    0.46
     Août
    0.46
     umožňuje
    0.46
    Activations Density 0.000%

    No Known Activations