© 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. 69518
    Prev
    Next
    INDEX
    Explanations

    location data and identifiers

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

    compared to, smaller than

    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
     لکھنے
    0.50
     نکال
    0.47
    𒀭
    0.47
     TimeUnit
    0.47
     yapacağız
    0.46
     возникает
    0.46
    醿
    0.46
     писатель
    0.46
    だと思います
    0.45
    وڈ
    0.45
    POSITIVE LOGITS
    lio
    0.54
    mare
    0.50
     LAN
    0.50
     Dist
    0.50
     Aires
    0.50
     Synt
    0.49
     Ó
    0.48
     Nex
    0.47
     NFC
    0.47
     Guar
    0.46
    Activations Density 0.001%

    No Known Activations