© 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. 196871
    Prev
    Next
    INDEX
    Explanations

    endings like 'nd' or 'ough'

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

    Decimal point and numbers

    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
    ים
    0.52
     Lega
    0.48
    שׁ
    0.46
    ס
    0.46
    ין
    0.45
    愆
    0.44
    лювання
    0.43
    ण्डा
    0.43
    INotification
    0.42
     Бекер
    0.42
    POSITIVE LOGITS
     mõ
    0.56
     kaks
    0.51
    kl
    0.48
     ela
    0.46
     स्पष्ट
    0.46
     bỏ
    0.46
     сне
    0.45
     regl
    0.45
    早
    0.45
     oğlu
    0.45
    Activations Density 0.000%

    No Known Activations