© 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. 59787
    Prev
    Next
    INDEX
    Explanations

    evaluation. sponsor. resulting. endless. complete. countries. arguing

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

    natural language sequences and structures

    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
    Ψ
    0.50
    öff
    0.49
    вий
    0.47
    GS
    0.47
    臊
    0.44
    ଈ
    0.43
    ρους
    0.42
    PSI
    0.42
    瑙
    0.42
    gs
    0.42
    POSITIVE LOGITS
     গত
    0.47
     এন্টি
    0.45
     एंटी
    0.44
     debajo
    0.44
     عین
    0.44
     অতিক্রম
    0.43
     શેર
    0.43
     بلکه
    0.42
     فرمان
    0.42
     ابتدا
    0.42
    Activations Density 0.000%

    No Known Activations