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. 40-GEMMASCOPE-2-RES-262K
    4. 17116
    Prev
    Next
    INDEX
    Explanations

    editor or reader publications

    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_40_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
     pokemon
    0.58
     fucked
    0.54
     touristic
    0.54
    pokemon
    0.52
     idk
    0.51
     hypothesis
    0.50
    🥲
    0.49
    🤭
    0.49
     semnific
    0.48
     Pokemon
    0.48
    POSITIVE LOGITS
     Editors
    0.78
     Editor
    0.71
    Editor
    0.71
     EDITOR
    0.69
    Editors
    0.66
     editors
    0.63
     editor
    0.60
     Reader
    0.59
     readers
    0.58
     lectores
    0.58
    Activations Density 0.003%

    No Known Activations