© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 104042
    Prev
    Next
    INDEX
    Explanations

    try to open and read

    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_16_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
    Ι
    0.78
    cancer
    0.69
    ο
    0.68
    done
    0.66
    diabetes
    0.64
    1
    0.63
    Ζ
    0.63
    7
    0.63
    IE
    0.61
    urg
    0.61
    POSITIVE LOGITS
     birch
    0.85
     reside
    0.64
     traite
    0.64
     tans
    0.63
     attempts
    0.62
     recre
    0.62
     delle
    0.61
     standard
    0.61
     analy
    0.61
     ornith
    0.61
    Activations Density 0.013%

    No Known Activations