© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35296
    Prev
    Next
    INDEX
    Explanations

    congenital conditions

    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_16_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
     carcinogenesis
    0.61
     t
    0.58
     DEST
    0.58
    겠습니다
    0.57
    ߋ
    0.57
     initiate
    0.57
     inflación
    0.56
    ها
    0.56
    颠
    0.56
    ве
    0.55
    POSITIVE LOGITS
    i
    1.03
    י
    0.94
    es
    0.88
    م
    0.88
    at
    0.85
    បន្ថ
    0.84
    et
    0.84
    iin
    0.79
    dba
    0.78
    _
    0.77
    Activations Density 0.004%

    No Known Activations