© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13086
    Prev
    Next
    INDEX
    Explanations

    structured explanations with bolded terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ‘
    2.42
    ”]
    2.22
    alade
    2.20
    lobal
    2.15
     ‌
    2.11
    ‍
    2.08
    ">'+
    2.07
    
    2.07
     “‘
    2.06
    …]
    2.06
    POSITIVE LOGITS
    蓣
    2.87
    䥑
    2.67
    ꞎ
    2.58
     kelamin
    2.55
    <unused560>
    2.51
     landlab
    2.51
    ꯔ
    2.47
    """,
    2.45
    ぇ
    2.45
    𝐫
    2.43
    Activations Density 0.096%

    No Known Activations