© 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. 239612
    Prev
    Next
    INDEX
    Explanations

    partner-loyal clients

    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
    corder
    0.48
    cas
    0.48
    穼
    0.47
    ”）
    0.46
    conversation
    0.45
    wherein
    0.45
     १४
    0.45
     नारा
    0.44
     त
    0.44
    sette
    0.44
    POSITIVE LOGITS
    螯
    0.48
     intersects
    0.47
     goble
    0.43
     faceted
    0.41
     vésicules
    0.40
    屹
    0.40
     dimensioni
    0.40
     rectangles
    0.40
    مرة
    0.40
    忔
    0.39
    Activations Density 0.000%

    No Known Activations