© 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. 175896
    Prev
    Next
    INDEX
    Explanations

    actions with outcomes

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

    outperforms, defeated, incorporated, generating

    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
     அப்படி
    0.48
     ഉണ്ട്
    0.47
     ಸಮಯ
    0.45
    手順
    0.45
    感じで
    0.45
     ಯಾವಾಗ
    0.45
    紂
    0.45
     가서
    0.44
     яхшы
    0.44
    句話
    0.43
    POSITIVE LOGITS
     zarówno
    0.55
    the
    0.54
     the
    0.54
    G
    0.50
    B
    0.48
     NYSE
    0.47
     B
    0.46
     K
    0.45
     L
    0.43
    The
    0.43
    Activations Density 0.129%

    No Known Activations