© 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. 5107
    Prev
    Next
    INDEX
    Explanations

    evaluate and ask

    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
    лы
    0.56
    ר
    0.55
    mathspace
    0.50
    जिसे
    0.49
     outra
    0.49
     もう
    0.48
    *}$
    0.47
    is
    0.47
    ܘ
    0.46
    रियो
    0.46
    POSITIVE LOGITS
     pod
    0.50
     ডু
    0.47
     ingot
    0.47
     kuts
    0.46
     boc
    0.46
     בש
    0.46
     pods
    0.45
     wartime
    0.44
     noc
    0.43
     ten
    0.43
    Activations Density 0.003%

    No Known Activations