© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2818
    Prev
    Next
    INDEX
    Explanations

    Solo Piano, revealed, weighted average, every, Operational Stage

    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_7_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
    xsl
    1.66
    .
    1.57
    addListener
    1.56
    
    1.48
    Operator
    1.42
     peringkat
    1.39
    ட்ச
    1.39
     admitted
    1.39
     العامل
    1.39
    0
    1.38
    POSITIVE LOGITS
    𒁉
    2.15
    त
    2.03
     brevity
    2.00
    𝒊
    1.95
    fnamefont
    1.93
    <unused1218>
    1.91
    <unused998>
    1.90
     NPTypeCode
    1.86
     punctuation
    1.85
    <unused1261>
    1.85
    Activations Density 0.030%

    No Known Activations