© 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. 6669
    Prev
    Next
    INDEX
    Explanations

    functions and requirements

    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
     ซึ่ง
    0.31
     thisobject
    0.31
    这
    0.31
    这个
    0.30
     యొక్క
    0.30
     thisStudent
    0.28
    ที่คุณ
    0.28
    <unused2169>
    0.27
     Büh
    0.27
    這個
    0.27
    POSITIVE LOGITS
     Requires
    0.41
     требует
    0.40
     used
    0.38
     extremely
    0.36
    Requires
    0.35
     requires
    0.34
     Provides
    0.33
     Allows
    0.33
     promotes
    0.33
    Can
    0.33
    Activations Density 1.849%

    No Known Activations