© 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. 10367
    Prev
    Next
    INDEX
    Explanations

    performance and tone

    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
    ဉ်
    2.06
    antera
    1.96
    “(
    1.93
    ger
    1.93
    й
    1.91
     tract
    1.90
    StateManager
    1.90
    (“
    1.88
    ங்கி
    1.87
     zah
    1.87
    POSITIVE LOGITS
    َب
    2.29
    STL
    2.04
    ustom
    2.02
    shid
    2.01
    亠
    1.99
    ставляет
    1.98
    lady
    1.98
    َل
    1.97
    िसो
    1.96
    শীল
    1.96
    Activations Density 0.000%

    No Known Activations