© 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. 156753
    Prev
    Next
    INDEX
    Explanations

    months and technical terms

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

    approximations and mathematical symbols

    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
     проходить
    0.50
     खूप
    0.45
    យ៉ាង
    0.45
    티브
    0.44
     paff
    0.42
    띠
    0.42
     ходить
    0.42
     exoner
    0.41
     Foil
    0.41
    IQUE
    0.40
    POSITIVE LOGITS
    Declar
    0.55
    Nau
    0.51
    Developers
    0.48
    ;
    0.47
    に応じて
    0.46
     Δε
    0.46
    Ste
    0.46
    Developer
    0.46
     enforcing
    0.46
    开发者
    0.46
    Activations Density 0.001%

    No Known Activations