© 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. 4756
    Prev
    Next
    INDEX
    Explanations

    So

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

    so,

    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
     interstitiis
    0.18
     adherents
    0.18
     نیز
    0.18
     precludes
    0.17
    、
    0.17
    ھا
    0.17
     (,
    0.16
                  
    0.16
     dépassant
    0.16
     fissures
    0.16
    POSITIVE LOGITS
     איך
    0.22
     THAT
    0.20
    そんな
    0.20
     EVERYTHING
    0.20
     you
    0.20
     정말
    0.20
    まずは
    0.20
    我們
    0.20
     усі
    0.19
     outta
    0.19
    Activations Density 0.554%

    No Known Activations