© 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. 239073
    Prev
    Next
    INDEX
    Explanations

    places and specific beings

    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
     ζω
    0.50
     пуль
    0.48
    攜
    0.47
     contactos
    0.46
     وما
    0.45
     جمهور
    0.45
     जमा
    0.44
     அம்ம
    0.43
     liquido
    0.43
     صدي
    0.43
    POSITIVE LOGITS
     Johnson
    0.48
     Bernoulli
    0.48
    сці
    0.46
    련
    0.46
    গে
    0.45
    Johnson
    0.45
     Bộ
    0.45
    سٹم
    0.44
     Hoboken
    0.44
     JOHNSON
    0.43
    Activations Density 0.000%

    No Known Activations