© 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. 23731
    Prev
    Next
    INDEX
    Explanations

    Markdown formatting

    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
    娠
    0.44
    ributor
    0.41
    ਲੀ
    0.41
     precaution
    0.40
     ഇതു
    0.40
    ريكي
    0.38
    вку
    0.38
    ારા
    0.38
     stav
    0.38
    沘
    0.38
    POSITIVE LOGITS
     Equation
    0.48
    cdots
    0.46
     Vielzahl
    0.42
    Teacher
    0.42
    Nb
    0.41
    9
    0.41
    Update
    0.40
    첫
    0.40
     Bre
    0.39
     첫
    0.39
    Activations Density 0.000%

    No Known Activations