© 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. 100842
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinal words

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

    describing the feel

    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
    фу
    0.54
    보
    0.51
    Ligações
    0.51
    LOSS
    0.50
    ૢ
    0.50
    פים
    0.49
    났
    0.49
    니
    0.48
    리
    0.48
    מו
    0.48
    POSITIVE LOGITS
     Day
    0.55
     Fab
    0.55
     Micron
    0.51
     Assembly
    0.50
     Communication
    0.50
     সেদিন
    0.50
     communication
    0.50
     Performance
    0.49
     Saturday
    0.49
     Marathon
    0.49
    Activations Density 0.003%

    No Known Activations