© 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. 16247
    Prev
    Next
    INDEX
    Explanations

    reading file content

    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
     Complaint
    0.41
    !]
    0.39
     编辑
    0.39
     Ditto
    0.38
     École
    0.37
     ή
    0.37
     化
    0.37
     σχ
    0.36
     enlarging
    0.36
     Commission
    0.35
    POSITIVE LOGITS
    ldg
    0.38
    ディング
    0.37
    ாச
    0.37
    amaged
    0.37
    robust
    0.36
    sekut
    0.36
    拮
    0.36
     கூட்ட
    0.35
    mmas
    0.35
     WILD
    0.35
    Activations Density 0.000%

    No Known Activations