© 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. 2888
    Prev
    Next
    INDEX
    Explanations

    universe: origin and composition

    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
    бора
    2.69
    überkü
    2.68
    ❿
    2.66
    swürdig
    2.49
    setCode
    2.40
    ㇂
    2.30
     KEYUP
    2.29
    зина
    2.28
    ᅣ
    2.28
    ﮄ
    2.28
    POSITIVE LOGITS
    ে
    3.80
    es
    3.80
    iya
    3.78
    eer
    3.67
    ي
    3.64
    as
    3.63
    iin
    3.51
    ۰
    3.47
    a
    3.46
    e
    3.45
    Activations Density 0.226%

    No Known Activations