© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 102387
    Prev
    Next
    INDEX
    Explanations

    LCD from

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

    gather documents, allow usage

    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
     различными
    0.51
    NANA
    0.49
    包装
    0.48
    ウェア
    0.46
     бойынша
    0.46
     впечат
    0.46
     играть
    0.46
    ']),
    0.45
    ')],
    0.45
     визна
    0.45
    POSITIVE LOGITS
    ۵
    0.50
     Aspen
    0.49
    REN
    0.48
    UNDS
    0.47
     a
    0.46
    elling
    0.45
    RC
    0.45
     benthic
    0.44
    ndon
    0.44
    ri
    0.44
    Activations Density 0.002%

    No Known Activations