© 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. 225037
    Prev
    Next
    INDEX
    Explanations

    party engaged

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

    Source, Title, or **

    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
    гает
    0.52
     работа
    0.48
    ிற
    0.48
     enthusiastic
    0.48
    람
    0.47
     выполняется
    0.46
     хотите
    0.45
     маги
    0.45
    вает
    0.44
    된다
    0.44
    POSITIVE LOGITS
     teammate
    0.50
     teammates
    0.44
     pathway
    0.43
     safely
    0.43
     situazioni
    0.42
     Weather
    0.41
     &/
    0.41
     Reaktion
    0.41
     weathered
    0.39
     Backyard
    0.39
    Activations Density 0.000%

    No Known Activations