© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8760
    Prev
    Next
    INDEX
    Explanations

    mathematical and code symbols

    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_9_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
     vực
    1.65
     déchir
    1.52
     fatto
    1.47
    ្នែក
    1.40
    
    1.38
    
    1.37
    ங்கிணை
    1.33
     smack
    1.32
    opold
    1.32
     dessen
    1.31
    POSITIVE LOGITS
    %%%%%%%%%%%%%%%%
    1.84
    %%%%%%%%%%%%
    1.76
    𝐢
    1.70
    ****************
    1.69
    ******
    1.60
    $('
    1.60
    ve
    1.60
    على
    1.60
    ********
    1.48
    %%%%%%%%
    1.47
    Activations Density 0.680%

    No Known Activations