© 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. 2993
    Prev
    Next
    INDEX
    Explanations

    selling items or stating conditions

    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
     artériel
    0.41
    োঁয়া
    0.41
    ایات
    0.40
    椏
    0.39
    ಲ್ಲು
    0.38
    ométrie
    0.38
     काळात
    0.38
    Під
    0.38
     Aktien
    0.37
     آئے
    0.37
    POSITIVE LOGITS
     de
    0.59
     l
    0.57
     (
    0.57
     S
    0.52
     V
    0.52
     a
    0.51
     T
    0.51
     N
    0.51
     D
    0.51
     K
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.