© 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. 2868
    Prev
    Next
    INDEX
    Explanations

    tiny and little descriptions

    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
    いる
    2.79
    
    2.61
    ildenafil
    2.57
    ranath
    2.51
    s
    2.48
    r
    2.39
    жений
    2.37
    чив
    2.35
    ደም
    2.35
    nesdays
    2.27
    POSITIVE LOGITS
    Ւ
    3.20
     onBackPressed
    2.54
    ɴ
    2.46
    瘩
    2.45
     sap
    2.42
    ISAM
    2.38
     devoir
    2.38
     Die
    2.37
     Der
    2.36
    Ễ
    2.31
    Activations Density 0.082%

    No Known Activations