© 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. 168166
    Prev
    Next
    INDEX
    Explanations

    Mr Shortcut, Options strategies

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

    Apple AFib detection

    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
    B
    0.51
    if
    0.46
     Más
    0.46
     Ở
    0.44
    A
    0.44
     பொருட்கள்
    0.44
     In
    0.42
    In
    0.42
     Bers
    0.42
     Dla
    0.42
    POSITIVE LOGITS
     شہری
    0.49
    httphttps
    0.48
     სპეცი
    0.47
     aaj
    0.46
     devre
    0.45
     OFDM
    0.45
    െടുത്തു
    0.44
     privati
    0.44
     DAVID
    0.44
    ㄳ
    0.44
    Activations Density 0.000%

    No Known Activations