© 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. 136201
    Prev
    Next
    INDEX
    Explanations

    slip down, stemware, retrospective exhibition, members engaged

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

    explaining difficulty ID

    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
     apr
    0.50
     junctions
    0.44
     sinist
    0.43
     tarm
    0.43
    benzo
    0.43
     wort
    0.43
     histo
    0.41
    ह
    0.41
    ੱ
    0.40
    gunaan
    0.40
    POSITIVE LOGITS
     przykład
    0.52
     ليس
    0.52
     приняли
    0.52
     مشترك
    0.50
    沛
    0.50
     объяс
    0.50
    ężczy
    0.49
    érin
    0.49
     অংশগ্রহণ
    0.49
     пыта
    0.48
    Activations Density 0.000%

    No Known Activations