© 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. 2873
    Prev
    Next
    INDEX
    Explanations

    well-descriptive compounds

    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
     acknowledge
    2.26
    acknowledge
    2.09
     convince
    2.09
    οι
    2.05
    ᴋ
    2.05
     produce
    2.04
     and
    2.01
    pollo
    2.00
     तो
    2.00
    乞
    1.97
    POSITIVE LOGITS
     quadrada
    2.17
    رل
    1.81
    कलन
    1.74
     	i
    1.69
     algebraica
    1.65
    宽度
    1.65
    riterion
    1.65
    entlich
    1.63
    શ્મી
    1.63
     centrale
    1.61
    Activations Density 0.369%

    No Known Activations