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. 1061
    Prev
    Next
    INDEX
    Explanations

    -us/ links

    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
    FindingsRequest
    0.88
    émique
    0.86
    umlah
    0.85
     publicó
    0.85
    iais
    0.83
    <unused411>
    0.83
     jugó
    0.83
    .??.??"]
    0.82
    êmement
    0.82
    ahanam
    0.82
    POSITIVE LOGITS
    *
    0.65
    **
    0.65
     If
    0.65
     Tablet
    0.64
    平日
    0.63
     You
    0.63
      
    0.61
     (
    0.61
    ;
    0.60
       
    0.58
    Activations Density 0.001%

    No Known Activations