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. 14712
    Prev
    Next
    INDEX
    Explanations

    specific data sources or reasons

    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
    עות
    0.47
     duis
    0.47
    alertDialog
    0.45
    adapter
    0.45
     FXMLLoader
    0.45
    ChoiceItemLayout
    0.45
    propan
    0.44
    塞
    0.43
    hoom
    0.42
    晝
    0.42
    POSITIVE LOGITS
     गुस्सा
    0.48
     Exactly
    0.44
     exactly
    0.42
     concerned
    0.41
     requesting
    0.41
     Scouts
    0.40
    깔
    0.40
     to
    0.40
     obj
    0.40
     demanding
    0.40
    Activations Density 0.000%

    No Known Activations