© 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-262K
    7. 79616
    Prev
    Next
    INDEX
    Explanations

    rescue, file, numbers, mort, 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
     связан
    0.47
     たら
    0.46
    *.
    0.45
    ande
    0.44
     Jahrhund
    0.44
    nal
    0.44
    ereur
    0.44
     Фор
    0.44
     άλλ
    0.43
     приви
    0.43
    POSITIVE LOGITS
     hydrolysis
    0.55
    ة
    0.54
     Synod
    0.48
    ing
    0.46
     fluctuation
    0.46
    ស់
    0.44
    чі
    0.44
     staple
    0.44
    ق
    0.43
     deliberation
    0.42
    Activations Density 0.000%

    No Known Activations