© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37083
    Prev
    Next
    INDEX
    Explanations

    MQL code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    رج
    0.46
    чник
    0.42
    ران
    0.41
     kool
    0.41
    inserts
    0.38
     같은
    0.38
    ='+
    0.38
    ডাক
    0.38
     windy
    0.38
    ]='
    0.38
    POSITIVE LOGITS
    પ
    0.48
     estadounidenses
    0.46
     preclude
    0.45
    ícias
    0.44
     integrand
    0.44
     videojuegos
    0.44
     posits
    0.44
    <0xAC>
    0.44
     foment
    0.44
     cortar
    0.44
    Activations Density 0.002%

    No Known Activations