© 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. 158791
    Prev
    Next
    INDEX
    Explanations

    code documentation and technical terms

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

    describing temporary or associated concepts

    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
    1
    0.48
    同年
    0.44
    信する
    0.43
    difference
    0.42
     必ず
    0.42
    થી
    0.41
    file
    0.41
    相
    0.41
    違い
    0.41
    其余
    0.41
    POSITIVE LOGITS
     vilka
    0.55
    agas
    0.48
     LOL
    0.48
     ikon
    0.48
    ektor
    0.47
    ్రీన్
    0.47
     propag
    0.46
     Afro
    0.46
     garlands
    0.46
     konte
    0.46
    Activations Density 0.001%

    No Known Activations