© 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. 151649
    Prev
    Next
    INDEX
    Explanations

    room for activities or spaces

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

    multi-head attention

    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
    ৰ
    0.47
     طويل
    0.45
     будет
    0.45
     будут
    0.44
     особенно
    0.44
     مای
    0.44
     после
    0.44
    루
    0.43
     Моло
    0.43
     здоров
    0.43
    POSITIVE LOGITS
     zusätz
    0.49
     zusätzlichen
    0.48
     aquifer
    0.42
     fãs
    0.42
     ferram
    0.42
    舶
    0.41
    嶈
    0.41
    जिस्ट
    0.40
     clash
    0.40
     treinamento
    0.40
    Activations Density 0.001%

    No Known Activations