© 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. 21599
    Prev
    Next
    INDEX
    Explanations

    Conference proceedings

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

    conference paper submission

    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
     rejuvenating
    0.53
     pathophysiology
    0.50
    गील
    0.50
     yuè
    0.50
    絊
    0.49
    la
    0.48
     rém
    0.47
    ら
    0.47
     buckling
    0.46
    रे
    0.45
    POSITIVE LOGITS
    Conference
    0.73
    conference
    0.71
     конференции
    0.70
     conference
    0.64
     конферен
    0.64
     Conference
    0.62
     konfer
    0.59
    conferences
    0.59
     Conferences
    0.59
     conférence
    0.59
    Activations Density 0.010%

    No Known Activations