© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65759
    Prev
    Next
    INDEX
    Explanations

    next expected

    np_acts-logits-general · gemini-2.5-flash-lite

    riddles or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dairy
    0.46
    ター
    0.46
    abouts
    0.46
    риа
    0.44
     casos
    0.44
    ма
    0.43
    대
    0.43
    ح
    0.43
    بانی
    0.43
    사
    0.43
    POSITIVE LOGITS
     nebude
    0.54
     赵
    0.46
    um
    0.46
     gebru
    0.46
    j
    0.45
    FileInputExcel
    0.45
     extinguisher
    0.45
     नव्ह
    0.44
    т
    0.44
    ៣
    0.44
    Activations Density 0.005%

    No Known Activations