© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54045
    Prev
    Next
    INDEX
    Explanations

    code, markup, and technical context

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

    the presence of numeric tokens (integers or decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    になれば
    -0.99
    стрі
    -0.93
    我
    -0.91
    imanapun
    -0.89
     (;;)
    -0.88
     muualla
    -0.84
    ０
    -0.84
    från
    -0.84
    inquirer
    -0.84
    場合は
    -0.84
    POSITIVE LOGITS
    と思った
    1.12
    そのため
    1.05
    はその
    1.02
    と思いました
    0.93
    風景
    0.90
     their
    0.88
    了不少
    0.87
    性質
    0.86
     see
    0.83
    その
    0.83
    Activations Density 0.010%

    No Known Activations