© 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. 219923
    Prev
    Next
    INDEX
    Explanations

    conference discussions

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

    Oahu

    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
    3
    0.57
    o
    0.52
     Deuter
    0.47
    4
    0.47
    ofy
    0.46
     Sá
    0.45
     Religions
    0.44
     Dol
    0.44
    hl
    0.43
     Zá
    0.43
    POSITIVE LOGITS
     commentaires
    0.50
    란
    0.49
     CONFERENCE
    0.49
     conferencia
    0.48
     conness
    0.47
    兗
    0.47
     conférence
    0.46
     nessun
    0.46
     conservar
    0.46
     ricerca
    0.46
    Activations Density 0.000%

    No Known Activations