© 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. 4599
    Prev
    Next
    INDEX
    Explanations

    structured text and code markers

    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
    gå
    0.35
     πάνω
    0.35
    ग्राहक
    0.35
     पाउडर
    0.34
    Jeśli
    0.33
    okolade
    0.33
    欢
    0.33
    䀨
    0.32
    สัตว์
    0.32
     अल्कोहल
    0.32
    POSITIVE LOGITS
    ↵
    0.41
     b
    0.33
     An
    0.32
     non
    0.31
     laptop
    0.30
    ↵↵
    0.30
     Laptop
    0.29
     Assumption
    0.29
     P
    0.29
     H
    0.29
    Activations Density 0.021%

    No Known Activations