© 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. 198255
    Prev
    Next
    INDEX
    Explanations

    Carrier, Merchant, holder

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

    adjective, budget, time commitment

    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
     institutions
    0.52
    ку
    0.50
     Institutions
    0.47
     instituciones
    0.47
    翠
    0.46
    hills
    0.45
    ورا
    0.43
    gre
    0.43
    гез
    0.43
     Dew
    0.42
    POSITIVE LOGITS
    umsi
    0.48
    Ə
    0.47
    TEMPLATE
    0.45
     যাবে
    0.45
     માંગ
    0.45
     paucity
    0.44
     humanos
    0.43
     científicos
    0.43
     weighty
    0.43
     публі
    0.42
    Activations Density 0.000%

    No Known Activations