© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 35349
    Prev
    Next
    INDEX
    Explanations

    hormone, labels, right?, Horizontal, lead

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     axonal
    0.43
     artériel
    0.43
    CompliancePolicy
    0.42
    }^{+}$
    0.42
    NoError
    0.41
    敵人
    0.40
     tcpHeader
    0.39
    ządu
    0.39
     mauris
    0.38
     εφαρ
    0.38
    POSITIVE LOGITS
     bur
    0.41
     outside
    0.40
    outside
    0.39
    ວ
    0.39
    㫧
    0.39
     मेड
    0.38
    Outside
    0.38
    ハンド
    0.38
     список
    0.38
    аб
    0.37
    Activations Density 0.000%

    No Known Activations