© 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. 162599
    Prev
    Next
    INDEX
    Explanations

    numbers, locations, descriptions

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

    after method calls or punctuation

    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
     oreilles
    0.55
     αλλά
    0.49
     topLine
    0.47
    δί
    0.47
     génération
    0.46
     पीढ़ी
    0.46
    ᅮ
    0.46
     évaluation
    0.46
     longitudinale
    0.46
     ظِلِّ
    0.46
    POSITIVE LOGITS
    3
    0.54
     Portuguese
    0.52
     Nervous
    0.51
     W
    0.50
    0.50
    టీఎం
    0.49
    ayaran
    0.49
     Connection
    0.48
     Nigerian
    0.48
    ListView
    0.47
    Activations Density 0.000%

    No Known Activations