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. 7538
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure

    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
    Foe
    0.44
     calves
    0.41
    AVLNode
    0.41
    যানী
    0.40
     gxh
    0.40
     त्वचा
    0.40
     hitters
    0.40
    ⌞
    0.39
    PlayerDataCache
    0.39
    垟
    0.39
    POSITIVE LOGITS
    section
    0.77
    maketitle
    0.67
     Section
    0.66
     Introduction
    0.63
    abstract
    0.61
    Introduction
    0.61
     section
    0.60
    Section
    0.57
    bigskip
    0.54
    page
    0.54
    Activations Density 0.002%

    No Known Activations