© 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. 111266
    Prev
    Next
    INDEX
    Explanations

    monitoring swapping

    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
    Б
    0.47
    urized
    0.46
     подклю
    0.45
    델
    0.45
    хия
    0.44
    স্তার
    0.44
    ślin
    0.44
     Locals
    0.44
    櫒
    0.43
    atever
    0.43
    POSITIVE LOGITS
    '
    0.50
    VII
    0.47
     احت
    0.45
     تحقق
    0.44
     previstas
    0.43
     गन्ना
    0.42
     envis
    0.42
     consistente
    0.41
    gee
    0.40
    gä
    0.40
    Activations Density 0.000%

    No Known Activations