© 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. 29367
    Prev
    Next
    INDEX
    Explanations

    event or process

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

    Assigns/describes weights

    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
     vreme
    0.55
    ８
    0.51
    ኰ
    0.47
     sezonie
    0.46
     stagione
    0.45
    ısınız
    0.45
     ۸
    0.44
    зя
    0.44
    ຮ
    0.44
     বৈশিষ্ট্য
    0.44
    POSITIVE LOGITS
    Cluster
    0.53
    Piece
    0.48
     Mixer
    0.48
    WithError
    0.48
    According
    0.47
    Event
    0.47
    AM
    0.47
    Anna
    0.46
    Proc
    0.46
    Clusters
    0.46
    Activations Density 0.000%

    No Known Activations