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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 1117
    Prev
    Next
    INDEX
    Explanations

    &# followed by digits

    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
    演
    0.76
    ន្ត
    0.76
    पेट
    0.69
    Par
    0.69
     परे
    0.65
     branched
    0.65
     मोहित
    0.64
     cone
    0.63
    sonian
    0.63
     reasoned
    0.63
    POSITIVE LOGITS
     &#
    1.08
    &#
    0.92
    xFF
    0.91
    ;&#
    0.90
    
    0.84
    xff
    0.81
    xD
    0.80
     
    0.77
     "&#
    0.77
    
    0.75
    Activations Density 0.003%

    No Known Activations