© 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. 50855
    Prev
    Next
    INDEX
    Explanations

    two primes

    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
     بقت
    0.44
    ays
    0.44
    (),
    0.44
    ≐
    0.43
    千
    0.42
     baie
    0.42
    ר
    0.42
    n
    0.42
     gep
    0.41
     depl
    0.41
    POSITIVE LOGITS
     Blackberry
    0.54
     Xiaomi
    0.54
    뽁
    0.51
     heatmap
    0.49
     WeChat
    0.48
    图像
    0.48
     Gameplay
    0.47
    Xiaomi
    0.47
     Shields
    0.47
     Sensors
    0.47
    Activations Density 0.000%

    No Known Activations