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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 4443
    Prev
    Next
    INDEX
    Explanations

    news anchor

    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
    Matthew
    0.48
    欬
    0.43
    Bridge
    0.43
    થા
    0.43
    JOUR
    0.42
    Architecture
    0.42
    タグ
    0.41
    Wallpaper
    0.41
    Deep
    0.40
    Problem
    0.40
    POSITIVE LOGITS
     $"
    0.48
     million
    0.46
     millions
    0.45
     burnt
    0.45
     guaranteed
    0.45
     poached
    0.43
     estimating
    0.43
     understood
    0.42
     innumerable
    0.42
     suffered
    0.42
    Activations Density 0.001%

    No Known Activations