© 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. 19393
    Prev
    Next
    INDEX
    Explanations

    statistical publisher

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

    lists of information

    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
    .....
    0.47
     it
    0.46
     пят
    0.46
    нды
    0.46
     beo
    0.46
    tir
    0.46
     .......
    0.45
    鲑
    0.44
     maks
    0.44
    त्रियों
    0.44
    POSITIVE LOGITS
    讓
    0.50
    statistical
    0.49
     князя
    0.49
    書店
    0.46
    publisher
    0.46
    mass
    0.44
    вами
    0.43
    出版社
    0.43
    Statistical
    0.43
    Anonymous
    0.42
    Activations Density 0.000%

    No Known Activations