© 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. 40295
    Prev
    Next
    INDEX
    Explanations

    x followed by code or symbol

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

    x =

    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
    ्रीय
    0.58
    あった
    0.56
     सपना
    0.56
    ων
    0.55
    ენტი
    0.55
    િંગ
    0.53
    ک
    0.53
     ಕೆಲ
    0.52
     संख
    0.52
     ਸਿੰ
    0.52
    POSITIVE LOGITS
     x
    0.80
     X
    0.77
     y
    0.66
     i
    0.64
     t
    0.57
    .
    0.56
     sp
    0.55
     z
    0.55
     Y
    0.54
     mas
    0.53
    Activations Density 0.046%

    No Known Activations