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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 166334
    Prev
    Next
    INDEX
    Explanations

    -otic, -omatic, -inal, -uctive, -magnetic, -conditional, -logical, -uous

    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
    -\
    0.46
    -\\
    0.42
    rimi
    0.38
     Shire
    0.37
     geführt
    0.37
     memanfaatkan
    0.37
    FUNC
    0.37
    Tat
    0.37
    func
    0.37
     푸
    0.37
    POSITIVE LOGITS
    ειας
    0.38
     ____
    0.38
    絖
    0.37
     Literacy
    0.37
     ³
    0.36
     Pron
    0.36
    ización
    0.35
     contrace
    0.35
     Muscles
    0.35
     Respuesta
    0.35
    Activations Density 0.023%

    No Known Activations