© 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. 222879
    Prev
    Next
    INDEX
    Explanations

    not worry after a negative, games, campuses

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

    various distinct 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
    猀
    0.45
    曰
    0.44
     असू
    0.43
    楽曲
    0.43
    ग्रस्त
    0.41
    🍾
    0.40
    ぞれ
    0.39
    そこに
    0.39
    ಫ
    0.39
    <unused432>
    0.38
    POSITIVE LOGITS
    ase
    0.50
    amasını
    0.45
    ol
    0.43
     অভিভাবকদের
    0.43
     ions
    0.42
    hh
    0.42
    ppings
    0.42
    ត្រូវការ
    0.42
     jego
    0.42
    tween
    0.42
    Activations Density 0.002%

    No Known Activations