© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76160
    Prev
    Next
    INDEX
    Explanations

    password files

    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_31_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
     l
    0.42
     gaat
    0.42
    <0xB1>
    0.42
     মাথায়
    0.41
     ra
    0.41
     handelt
    0.40
    妨
    0.39
     mim
    0.39
     মাথায়
    0.38
     asa
    0.38
    POSITIVE LOGITS
    潑
    0.47
    เมตร
    0.46
    รม
    0.44
     petición
    0.44
    チック
    0.43
     preachers
    0.43
    IQ
    0.43
    İK
    0.43
    ‸
    0.42
    Healthcare
    0.42
    Activations Density 0.000%

    No Known Activations