© 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. 193464
    Prev
    Next
    INDEX
    Explanations

    component class

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

    Sincerely, Server, architecture, DOCSIS

    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
     pozitiv
    0.55
    ເອ
    0.55
     ያል
    0.55
    <unused23>
    0.54
    ﻪ
    0.54
     pozit
    0.53
    㮔
    0.53
     නි
    0.52
    navigationLinks
    0.52
     доходов
    0.52
    POSITIVE LOGITS
    y
    0.56
    aw
    0.54
    1
    0.52
    ut
    0.49
    is
    0.48
    op
    0.48
    P
    0.48
    SR
    0.47
    ad
    0.46
    fallen
    0.46
    Activations Density 0.001%

    No Known Activations