© 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. 248075
    Prev
    Next
    INDEX
    Explanations

    largest wetland, five seasons, killed his

    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
     clever
    0.49
     {
    0.46
    лед
    0.43
     teaming
    0.43
    ेशनल
    0.43
     \
    0.43
    У
    0.42
    ẵn
    0.41
    のお店
    0.41
     لأ
    0.41
    POSITIVE LOGITS
     Equity
    0.55
     Zahlung
    0.52
    TableViewCell
    0.49
    imov
    0.47
    Nazi
    0.46
     mastect
    0.46
     Fulfillment
    0.45
     Einwill
    0.45
    Aid
    0.44
     シュ
    0.44
    Activations Density 0.000%

    No Known Activations