© 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. 173484
    Prev
    Next
    INDEX
    Explanations

    search for

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

    check current

    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
    ετε
    0.50
    wany
    0.41
    Attrition
    0.41
    сний
    0.40
    saturated
    0.40
    OnClickListener
    0.39
    []{
    0.39
    сет
    0.38
    wam
    0.38
    gazebo
    0.38
    POSITIVE LOGITS
    ړه
    0.43
     Feuilles
    0.43
    വ്
    0.43
     albo
    0.42
     decía
    0.42
     Faisal
    0.42
     ෆ
    0.41
     முஸ்
    0.41
     guerra
    0.41
     vrijed
    0.41
    Activations Density 0.000%

    No Known Activations