© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 122
    Prev
    Next
    INDEX
    Explanations

    RNAseq, Illumina NovaSeq

    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
    \'
    1.57
     アメリカ
    1.23
    '
    1.21
    (#
    1.19
    （
    1.08
    〓
    1.08
    '{
    1.07
    │
    1.06
     (/
    1.06
    `
    1.05
    POSITIVE LOGITS
    MPs
    1.33
    fallback
    1.25
    少ない
    1.25
     هناخد
    1.22
    ენტ
    1.20
    DUCED
    1.19
    ODO
    1.19
    ड्यू
    1.18
    overlap
    1.17
    parsed
    1.17
    Activations Density 0.000%

    No Known Activations