© 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. 154551
    Prev
    Next
    INDEX
    Explanations

    facts about Orange County

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

    famous musicians and singers

    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
     dugout
    0.46
     Coordinator
    0.43
    으니
    0.42
     chàng
    0.41
     cargoes
    0.41
    abspath
    0.41
    ま
    0.41
     スタッドレス
    0.41
    자는
    0.40
     রয়েছে
    0.40
    POSITIVE LOGITS
    itures
    0.46
    reszt
    0.46
    RIAL
    0.45
    ్రియ
    0.45
    燾
    0.44
     sensibil
    0.44
    يروس
    0.44
    奈
    0.43
    REAM
    0.43
    кна
    0.43
    Activations Density 0.002%

    No Known Activations