© 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. 5096
    Prev
    Next
    INDEX
    Explanations

    annotations and separators

    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
    𝗶
    0.58
    मुना
    0.54
    𝙸
    0.53
     Pré
    0.50
     množství
    0.50
    ớp
    0.49
    ITZ
    0.48
    𝒊
    0.48
    òria
    0.48
    兕
    0.47
    POSITIVE LOGITS
    *
    0.44
     Access
    0.44
    agog
    0.44
    ↵
    0.44
    otions
    0.44
    ho
    0.44
     access
    0.44
    client
    0.44
    migrations
    0.43
    w
    0.43
    Activations Density 0.000%

    No Known Activations