© 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. 40-GEMMASCOPE-2-RES-262K
    7. 16364
    Prev
    Next
    INDEX
    Explanations

    code snippets and commands

    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_40_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
    峮
    0.40
     Institut
    0.39
     Gesellschaft
    0.37
    ped
    0.36
    風
    0.36
     Oct
    0.35
    APPROVED
    0.35
     sebel
    0.34
    nehmen
    0.34
     Univer
    0.34
    POSITIVE LOGITS
     corros
    0.43
    SXml
    0.40
    ſs
    0.39
    }[
    0.39
     सीक्व
    0.38
    ::_
    0.38
    [,
    0.37
    WithOptions
    0.37
    <unused2155>
    0.36
    Shadow
    0.36
    Activations Density 0.000%

    No Known Activations