© 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. 41182
    Prev
    Next
    INDEX
    Explanations

    timestamps with timezone offsets

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

    date and time strings

    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
     देण्यासाठी
    0.47
    chée
    0.47
     २
    0.45
    <unused80>
    0.44
    Ბ
    0.44
     ૧
    0.44
     અર
    0.43
    Լ
    0.43
    柣
    0.43
    <unused52>
    0.42
    POSITIVE LOGITS
     bounced
    0.47
     +
    0.44
     bounce
    0.44
     bouncing
    0.42
     o
    0.40
     cof
    0.39
     strolling
    0.38
     immediacy
    0.37
     cancell
    0.37
     business
    0.36
    Activations Density 0.000%

    No Known Activations