© 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. 10297
    Prev
    Next
    INDEX
    Explanations

    states of being and actions

    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
    <bos>
    2.15
     gravedad
    2.04
     ক্ষয়ক্ষতি
    1.97
     poderão
    1.96
     constituyen
    1.91
    𝙫
    1.91
     deverá
    1.89
    স্র
    1.88
     homogé
    1.88
    tener
    1.87
    POSITIVE LOGITS
    ic
    1.88
     بال
    1.79
     of
    1.70
    ،
    1.68
    andra
    1.63
     with
    1.62
     على
    1.60
     ل
    1.59
     on
    1.59
     на
    1.58
    Activations Density 0.107%

    No Known Activations