© 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. 179221
    Prev
    Next
    INDEX
    Explanations

    learn their prices

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

    authorizations, PDFs, requirement, promise

    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
     curviliné
    0.53
    organisme
    0.52
    🔛
    0.52
    🕶
    0.51
    زمین
    0.50
    веря
    0.50
     მათ
    0.50
    ▟
    0.50
    嘉宾
    0.49
    గ్రహ
    0.49
    POSITIVE LOGITS
    b
    0.58
     trials
    0.55
    m
    0.54
     th
    0.53
    y
    0.50
    CI
    0.50
     b
    0.47
    j
    0.47
    0.47
     Set
    0.47
    Activations Density 0.001%

    No Known Activations