© 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. 53-GEMMASCOPE-2-RES-262K
    7. 10238
    Prev
    Next
    INDEX
    Explanations

    cu or cu leading words

    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_53_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
     ओर
    0.37
     Harvesting
    0.37
     हुए
    0.36
     Wann
    0.36
    櫒
    0.36
    鯰
    0.36
    ((\
    0.36
    iť
    0.36
     आग
    0.35
    BleStatus
    0.35
    POSITIVE LOGITS
    Cu
    0.78
     Cu
    0.75
     cu
    0.71
     CU
    0.64
    CU
    0.63
    cu
    0.61
     ку
    0.55
    зне
    0.52
    Ку
    0.52
    adrat
    0.49
    Activations Density 0.019%

    No Known Activations