© 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. 89308
    Prev
    Next
    INDEX
    Explanations

    document structure

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

    breakdown of types, sections, or categories

    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
     ਅ
    0.50
    cuando
    0.45
     Anche
    0.44
    doesn
    0.44
     Dong
    0.44
    不存在
    0.42
     চাহ
    0.42
    does
    0.42
     Cuando
    0.41
    porque
    0.41
    POSITIVE LOGITS
    Surprisingly
    0.47
    Bets
    0.46
    하신
    0.45
    깃
    0.44
    뽐
    0.44
     excavations
    0.43
     anvil
    0.43
     stoneware
    0.43
    귓
    0.43
     sledge
    0.43
    Activations Density 0.001%

    No Known Activations