© 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. 137921
    Prev
    Next
    INDEX
    Explanations

    links, data, generation

    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
    addies
    0.44
     এইসব
    0.41
     πως
    0.39
    cutaneous
    0.39
    的就是
    0.38
    譙
    0.38
    astically
    0.38
    作
    0.38
     LDGs
    0.37
    oxicity
    0.37
    POSITIVE LOGITS
    ठमाड
    0.48
    boxed
    0.44
    fæ
    0.44
    <bbox>
    0.44
     numeric
    0.44
    kanı
    0.42
    ሒ
    0.42
     изменений
    0.42
    艋
    0.42
     veze
    0.42
    Activations Density 0.006%

    No Known Activations