© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 47
    Prev
    Next
    INDEX
    Explanations

    introduces problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '
    0.34
     a
    0.32
     the
    0.31
    0
    0.29
    y
    0.29
     maximum
    0.28
    EN
    0.28
    n
    0.27
    /
    0.27
     b
    0.27
    POSITIVE LOGITS
    
    0.37
    says
    0.34
    といった
    0.32
     powiedział
    0.31
    ática
    0.31
     Obwohl
    0.30
     என்கிறார்
    0.30
    <unused44>
    0.29
    akarane
    0.29
    と言
    0.28
    Activations Density 0.504%

    No Known Activations