© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 55297
    Prev
    Next
    INDEX
    Explanations

    protocol URLs and common collocations

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

    explaining or understanding

    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
     гиб
    0.46
    鲶
    0.43
     cuch
    0.43
    出品
    0.42
     aberr
    0.42
     defectos
    0.42
    艺术家
    0.42
    getDescription
    0.42
     chiqar
    0.41
     माँ
    0.41
    POSITIVE LOGITS
    м
    0.67
    т
    0.61
    те
    0.60
    да
    0.55
    ред
    0.54
    তে
    0.54
    ме
    0.52
    не
    0.50
    ాలలో
    0.49
    ко
    0.49
    Activations Density 0.001%

    No Known Activations