© 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. 13011
    Prev
    Next
    INDEX
    Explanations

    continue to

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

    continues to

    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
     Eventually
    0.63
     아주
    0.63
     beginnt
    0.58
     beginnen
    0.57
     acabou
    0.57
     încep
    0.55
     ၂
    0.54
     원래
    0.54
     ৫
    0.52
     aveva
    0.52
    POSITIVE LOGITS
    the
    0.91
    T
    0.84
    u
    0.75
    W
    0.73
    D
    0.72
    an
    0.71
    w
    0.71
    ts
    0.71
    ה
    0.71
    日々
    0.71
    Activations Density 0.059%

    No Known Activations