© 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. 196835
    Prev
    Next
    INDEX
    Explanations

    code snippets and documentation

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

    assignments and delimiters

    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
     автоматтары
    0.45
     изделий
    0.43
     имеется
    0.42
     цепо
    0.41
     изделия
    0.41
    に対し
    0.40
    Ⲉ
    0.40
    佲
    0.39
     листа
    0.39
    ํา
    0.38
    POSITIVE LOGITS
    v
    0.48
    crest
    0.47
    response
    0.47
    tic
    0.46
    reactive
    0.45
     প্রথমেই
    0.45
    first
    0.44
     loca
    0.44
    тесь
    0.43
    th
    0.43
    Activations Density 0.000%

    No Known Activations