© 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. 234354
    Prev
    Next
    INDEX
    Explanations

    preliminary or initial stages

    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
     consistente
    0.48
    composition
    0.46
    ቋ
    0.45
    σης
    0.45
     kèo
    0.45
    ન
    0.45
    gov
    0.45
     dring
    0.45
    اكم
    0.44
    Sri
    0.44
    POSITIVE LOGITS
     предвари
    0.54
     پای
    0.46
     ຂ
    0.45
     مرحله
    0.44
    ปรา
    0.44
    找到
    0.43
    初步
    0.43
    จะต้อง
    0.43
    范围
    0.43
     หา
    0.42
    Activations Density 0.001%

    No Known Activations