© 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. 191505
    Prev
    Next
    INDEX
    Explanations

    They are

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

    feasibility and capabilities

    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
    த்த
    0.50
     страни
    0.47
     ब्रह्म
    0.46
     небо
    0.46
    γο
    0.46
     диф
    0.45
     функцию
    0.45
    笃
    0.45
     фо
    0.43
     безопасности
    0.43
    POSITIVE LOGITS
     timeframe
    0.53
     available
    0.51
     omnichannel
    0.49
     আদৌ
    0.48
     existing
    0.48
     specific
    0.48
     chained
    0.48
     mire
    0.47
     কমপক্ষে
    0.47
     least
    0.46
    Activations Density 0.000%

    No Known Activations