© 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. 181811
    Prev
    Next
    INDEX
    Explanations

    segments of, signal sounds, structure in, starting to, choose to, MLC Regulations, Info icon

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

    mobile devices, Content Authors

    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
     l
    0.54
    </h4>
    0.50
     water
    0.46
     anv
    0.45
     pros
    0.44
     metaphors
    0.44
     membership
    0.44
     pale
    0.44
    暐
    0.44
     doubly
    0.44
    POSITIVE LOGITS
    gstatic
    0.54
    াদেশিক
    0.48
    хів
    0.47
    cza
    0.47
    ন্না
    0.46
    ঞ্চলিক
    0.46
    ceau
    0.45
     کا
    0.45
    Along
    0.44
    xrightarrow
    0.44
    Activations Density 0.001%

    No Known Activations