© 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. 10358
    Prev
    Next
    INDEX
    Explanations

    explaining a way of doing something

    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
    و
    3.23
    obacillus
    2.97
    ू
    2.95
    ו
    2.94
    ১
    2.90
    ozygous
    2.88
    íb
    2.80
    ك
    2.70
    ীয়
    2.64
     नरेंद्र
    2.60
    POSITIVE LOGITS
    ந்த
    2.39
    meshgrid
    2.38
    POR
    2.31
     ble
    2.30
    hips
    2.28
    AWSJavaScriptSDK
    2.27
    ᐟ
    2.22
    馭
    2.22
    PS
    2.20
    ﻉ
    2.20
    Activations Density 0.009%

    No Known Activations