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. 20414
    Prev
    Next
    INDEX
    Explanations

    citations and names

    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
    䄳
    0.47
    IDTH
    0.47
     ट्रॉप
    0.46
     कॉमे
    0.45
    デフォルト
    0.45
     各
    0.44
    运营商
    0.44
    Scenes
    0.44
    🐽
    0.44
    लीवुड
    0.43
    POSITIVE LOGITS
     Smith
    1.08
    Smith
    0.95
     Zhang
    0.95
     Wang
    0.93
    Zhang
    0.91
     Johnson
    0.86
     Jones
    0.86
     Sharma
    0.85
     Liu
    0.85
     Singh
    0.84
    Activations Density 0.005%

    No Known Activations