© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 32025
    Prev
    Next
    INDEX
    Explanations

    hardcoded credentials

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ಂತ್
    0.40
     utilizzato
    0.39
     gah
    0.37
    夗
    0.36
     정의
    0.35
     定义
    0.35
    摘要
    0.35
    GA
    0.35
    বিদ্যাল
    0.35
    влека
    0.35
    POSITIVE LOGITS
    mez
    0.40
     Hearts
    0.38
    Getty
    0.38
    Precis
    0.38
    Bedroom
    0.38
    amas
    0.37
    Bracket
    0.37
     hearts
    0.37
     Schol
    0.37
    amour
    0.37
    Activations Density 0.041%

    No Known Activations