© 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. 120922
    Prev
    Next
    INDEX
    Explanations

    apply to data

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

    qualifiers for description

    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
    Nueva
    0.54
    كا
    0.50
    Their
    0.49
    Nuevo
    0.49
    Bars
    0.49
    Univ
    0.47
    ه
    0.46
    য়ার
    0.46
     Frage
    0.45
    抽象
    0.45
    POSITIVE LOGITS
    étrico
    0.48
    菪
    0.45
    üş
    0.44
    <0xA2>
    0.43
     ۴
    0.43
     sporadically
    0.43
     partying
    0.43
     nostalgic
    0.43
     सिराज
    0.43
    şı
    0.42
    Activations Density 0.000%

    No Known Activations