© 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. 60279
    Prev
    Next
    INDEX
    Explanations

    a few time ago

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

    few followed by types or examples

    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
     a
    1.16
     I
    0.97
     i
    0.82
     an
    0.81
     F
    0.77
     B
    0.74
     K
    0.74
     M
    0.74
     Ə
    0.74
     Argentine
    0.72
    POSITIVE LOGITS
    몇
    1.13
    几
    0.96
    你
    0.87
     wenigen
    0.82
    幾個
    0.80
    幾
    0.80
    t
    0.79
    يد
    0.79
    ар
    0.79
     dozen
    0.78
    Activations Density 0.085%

    No Known Activations