Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169489
    Prev
    Next
    INDEX
    Explanations

    innovation and learning

    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
    ;
    0.56
    T
    0.49
    utions
    0.46
    ifications
    0.46
    Agg
    0.46
    ั
    0.46
    Spec
    0.44
    R
    0.44
     Specifications
    0.43
    Prosec
    0.43
    POSITIVE LOGITS
     vitally
    0.54
    :"
    0.50
    环节
    0.48
     conecta
    0.48
     वैधता
    0.47
    ୈ
    0.47
     caractér
    0.46
     कार्यक्रम
    0.46
     ദുൽ
    0.46
     zetten
    0.46
    Activations Density 0.003%

    No Known Activations