© 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. 34852
    Prev
    Next
    INDEX
    Explanations

    responsibilities and transitions

    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
    ท่อง
    0.49
     gelungen
    0.49
     ಮೂಲಕ
    0.47
     conosc
    0.46
     consigue
    0.45
     continuamente
    0.44
    Biblioteca
    0.44
     க
    0.44
    Recovery
    0.44
     engender
    0.44
    POSITIVE LOGITS
     CEOs
    0.52
    will
    0.51
     CEO
    0.47
     Kardashians
    0.46
     Kardashian
    0.45
     CFO
    0.45
     will
    0.43
    प्पू
    0.43
    ेट्टी
    0.42
     Mahomes
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.