© 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. 50911
    Prev
    Next
    INDEX
    Explanations

    SQL FROM clause entity

    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
     recogida
    0.46
     nedostat
    0.42
    ldecode
    0.42
    الي
    0.42
    Tak
    0.41
    ้
    0.41
    🎬
    0.41
    Tah
    0.40
    Codigo
    0.40
    冒
    0.40
    POSITIVE LOGITS
     plantations
    0.44
     laboratories
    0.41
     మాట్లా
    0.41
     respected
    0.40
     studios
    0.40
    ,))
    0.40
     subsystems
    0.39
     thence
    0.39
     palaces
    0.39
     afore
    0.38
    Activations Density 0.007%

    No Known Activations