© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13750
    Prev
    Next
    INDEX
    Explanations

    official documents and correspondence

    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_16k_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
    Jar
    0.42
    <unused2013>
    0.42
    盐
    0.41
    关联
    0.41
    ؛
    0.39
    ;/
    0.38
    Ralph
    0.38
     incurred
    0.37
     부분이
    0.37
    为
    0.37
    POSITIVE LOGITS
     galaxy
    0.57
     bazaar
    0.47
     demande
    0.47
     trillion
    0.45
     shameless
    0.44
     desea
    0.44
     homely
    0.43
     galaxies
    0.42
     freezed
    0.42
     monochrome
    0.41
    Activations Density 0.034%

    No Known Activations