© 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. 111771
    Prev
    Next
    INDEX
    Explanations

    MPP model

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

    knowledge cutoff September 2021

    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
     situazione
    0.56
    ﺍ
    0.53
    奈良
    0.51
    嚆
    0.47
     كانوا
    0.46
    ようになって
    0.45
     aparentemente
    0.45
    அ
    0.45
    ோது
    0.45
    錘
    0.45
    POSITIVE LOGITS
     trimester
    0.53
     角
    0.50
     agility
    0.49
     Voucher
    0.46
    ulsion
    0.46
    LocalDateTime
    0.46
     eprintln
    0.46
     greater
    0.46
     type
    0.45
     AsyncStorage
    0.45
    Activations Density 0.000%

    No Known Activations