© 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. 202443
    Prev
    Next
    INDEX
    Explanations

    thing or than

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

    thin comparison or imports

    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
     abhiv
    0.50
    a
    0.49
    papier
    0.48
    ’
    0.48
     alamu
    0.47
    adhesive
    0.47
     কাগজ
    0.46
     Chirurg
    0.46
     Empres
    0.46
    加大
    0.46
    POSITIVE LOGITS
    பெ
    0.47
     سته
    0.45
     וה
    0.44
    iforme
    0.44
    ist
    0.44
     ל
    0.44
     لینے
    0.43
     ות
    0.43
     lh
    0.43
     تین
    0.43
    Activations Density 0.002%

    No Known Activations