© 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. 10281
    Prev
    Next
    INDEX
    Explanations

    legal consequences and restrictions

    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
    কানিক্যাল
    2.69
    eo
    2.59
    ﮄ
    2.35
    ння
    2.35
    daad
    2.34
    inger
    2.33
    瘍
    2.24
    အစား
    2.23
    ャ
    2.20
    ത്ത്
    2.20
    POSITIVE LOGITS
     agreg
    2.85
     actu
    2.80
    на
    2.76
    йга
    2.70
    ဝ်
    2.69
    GOR
    2.68
     हट
    2.62
    niest
    2.62
     माध्यम
    2.62
    ̉a
    2.61
    Activations Density 0.002%

    No Known Activations