© 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. 4023
    Prev
    Next
    INDEX
    Explanations

    paper citations and references

    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
    Negative Logits
    ड़ा
    1.60
    ريقه
    1.58
    შ
    1.58
     प्रकारे
    1.55
    它的
    1.55
    钱
    1.45
    祷
    1.45
     डा
    1.44
    ឿង
    1.42
     Mostly
    1.41
    POSITIVE LOGITS
    และ
    2.17
     lainnya
    2.17
    ของ
    2.16
    isateur
    2.12
    ities
    2.09
    IZED
    2.07
     dari
    1.99
     bagi
    1.97
     yang
    1.97
     của
    1.94
    Activations Density 0.019%

    No Known Activations