© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52293
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning and combinations related to probability problems.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    mathematical expressions and calculations

    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_65k_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
     microorganisms
    0.42
     ممالک
    0.41
     Chromatography
    0.40
    តិ
    0.40
    jvm
    0.39
    >%
    0.39
     ორგანო
    0.39
    孳
    0.39
    issaient
    0.38
    kingdom
    0.38
    POSITIVE LOGITS
     shock
    0.43
     model
    0.42
     pseudo
    0.41
     Cinco
    0.40
    Доб
    0.40
     apprentice
    0.40
     Ricardo
    0.39
    配备
    0.38
     đón
    0.38
    луйста
    0.38
    Activations Density 0.099%

    No Known Activations