© 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. 90552
    Prev
    Next
    INDEX
    Explanations

    events and venues

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

    think of examples

    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
     Fläche
    0.47
    isations
    0.45
    迠
    0.44
    дел
    0.43
     Giải
    0.43
     собою
    0.43
    пин
    0.42
     Đế
    0.42
    坷
    0.42
    သာ
    0.42
    POSITIVE LOGITS
    Objects
    0.50
    Estos
    0.49
    Eight
    0.48
    Seven
    0.48
    Nous
    0.45
    Tecla
    0.45
    Five
    0.45
    Archives
    0.45
    Collecting
    0.45
    Carbon
    0.44
    Activations Density 0.000%

    No Known Activations