© 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
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8689
    Prev
    Next
    INDEX
    Explanations

    non-english characters and 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
    en
    1.19
    ු
    1.16
    
    1.12
     suffice
    1.08
     greats
    1.05
     schematically
    1.04
     hề
    1.03
    zość
    1.03
     tudi
    1.00
    া
    1.00
    POSITIVE LOGITS
    ոն
    0.99
     etc
    0.99
    М
    0.95
    etc
    0.93
    ประกอบ
    0.92
     $*$
    0.91
    $.\
    0.91
    FF
    0.91
    $.
    0.90
    нима
    0.89
    Activations Density 0.601%

    No Known Activations