© 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. 64565
    Prev
    Next
    INDEX
    Explanations

    international catwalks

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

    DIY Mother's Day gifts

    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
    пи
    0.55
    Services
    0.52
     ভাইস
    0.50
    Tonel
    0.50
    ጁ
    0.49
    Universe
    0.47
    Vice
    0.47
    Navigation
    0.47
    Turning
    0.46
    послед
    0.46
    POSITIVE LOGITS
    al
    0.45
    ುವುದಿಲ್ಲ
    0.44
     dimensionless
    0.44
     Cummins
    0.43
    езд
    0.43
     smoky
    0.42
    <unused2121>
    0.41
     Nile
    0.40
     IAEA
    0.39
    เล่น
    0.39
    Activations Density 0.000%

    No Known Activations