© 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. 19929
    Prev
    Next
    INDEX
    Explanations

    corollaries and coroutines

    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
     FALL
    0.58
     Falls
    0.50
    Falls
    0.49
    FALL
    0.48
     falls
    0.47
     fall
    0.46
     jatuh
    0.45
    落
    0.45
    Fall
    0.44
    幽
    0.43
    POSITIVE LOGITS
     cor
    1.88
     Cor
    1.70
    Cor
    1.65
     Corollary
    1.64
     corollary
    1.63
    cor
    1.58
    Corollary
    1.53
    corollary
    1.52
     кор
    1.48
     COR
    1.48
    Activations Density 0.003%

    No Known Activations