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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 762
    Prev
    Next
    INDEX
    Explanations

    hold onto things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    રી
    0.95
    Lack
    0.94
    bli
    0.92
    મે
    0.90
    carbonyl
    0.89
    lack
    0.87
    զ
    0.85
    済
    0.85
    ح
    0.85
    ত্ম
    0.85
    POSITIVE LOGITS
     aloft
    2.12
     sway
    2.03
     onto
    1.90
     accountable
    1.77
     hostage
    1.69
     steady
    1.54
     captive
    1.49
     grudge
    1.46
     tight
    1.45
     hold
    1.40
    Activations Density 0.046%

    No Known Activations