© 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. 202595
    Prev
    Next
    INDEX
    Explanations

    remainder of quantity

    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
    ب
    0.50
    د
    0.43
    م
    0.42
    الن
    0.42
    ال
    0.41
    ቀም
    0.41
    渶
    0.41
    فن
    0.41
    （
    0.41
    淘
    0.41
    POSITIVE LOGITS
     tuyên
    0.53
     manufact
    0.48
     producción
    0.46
     hare
    0.46
     sash
    0.45
     twenty
    0.45
     sobra
    0.45
     groove
    0.44
    ಕಾ
    0.44
    urende
    0.44
    Activations Density 0.000%

    No Known Activations