© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19724
    Prev
    Next
    INDEX
    Explanations

    units and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    шымта
    0.42
    rasekhar
    0.41
    SequentialGroup
    0.41
     alttext
    0.41
    蜥
    0.41
    echolog
    0.39
     polytope
    0.38
    学家
    0.38
    োগ্রাফ
    0.38
     thePack
    0.38
    POSITIVE LOGITS
    o
    0.41
    you
    0.39
    !)
    0.39
     bạn
    0.39
     onda
    0.38
     Hindi
    0.38
    en
    0.37
     atta
    0.37
    ...)
    0.36
     hindi
    0.36
    Activations Density 0.001%

    No Known Activations