© 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. 11750
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and functions

    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
     Почему
    0.37
    arla
    0.36
     bebe
    0.35
    CHICAGO
    0.35
     chocolates
    0.35
     উত্তরে
    0.34
     සහිත
    0.34
     ඇ
    0.34
    kezi
    0.34
     bebek
    0.34
    POSITIVE LOGITS
    ének
    0.41
     bijection
    0.38
    égard
    0.35
     bijective
    0.34
    נד
    0.34
     surjective
    0.34
    Eval
    0.34
    École
    0.34
    δή
    0.33
    န်
    0.33
    Activations Density 0.001%

    No Known Activations