© 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. 182349
    Prev
    Next
    INDEX
    Explanations

    create, declare, compute, record

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

    {Cisco, DL, GPU} models

    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
    igit
    0.50
    emotional
    0.49
    akos
    0.47
    شاء
    0.46
    agir
    0.46
    ﺸ
    0.46
    uş
    0.45
    shit
    0.45
    shay
    0.45
    قیق
    0.45
    POSITIVE LOGITS
     Create
    0.49
    佔
    0.47
    測試
    0.47
     районов
    0.46
     Notas
    0.46
    壓
    0.46
     Cámara
    0.46
     Comput
    0.45
     Declare
    0.44
     czasie
    0.44
    Activations Density 0.000%

    No Known Activations