© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 693
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
     probabilistic
    0.83
    Prob
    0.82
    beam
    0.80
     riddle
    0.79
     khám
    0.78
     راز
    0.78
    Trunc
    0.78
    腼
    0.78
     covariates
    0.78
     기준으로
    0.77
    POSITIVE LOGITS
     protesting
    2.46
     protest
    2.32
     protested
    2.29
     protests
    2.17
     petition
    2.11
     lobbying
    2.11
     Protest
    2.05
     advocacy
    2.03
     petitions
    2.00
     petitioned
    1.95
    Activations Density 2.277%

    No Known Activations