© 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. 46406
    Prev
    Next
    INDEX
    Explanations

    Lists items

    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
     чуть
    0.43
     ovation
    0.42
     vysok
    0.41
    ル
    0.41
    น
    0.39
    ul
    0.38
     Aleg
    0.38
     proteção
    0.38
     ríg
    0.38
    ए
    0.38
    POSITIVE LOGITS
     Types
    0.42
    Types
    0.41
     Terms
    0.40
     administrator
    0.38
    ］
    0.38
    >]</
    0.37
    參数
    0.37
    州市
    0.36
    称为
    0.36
    ictionnaire
    0.36
    Activations Density 0.073%

    No Known Activations