© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11426
    Prev
    Next
    INDEX
    Explanations

    require vendor/autoload

    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
    ,
    2.08
     P
    1.81
     On
    1.75
     life
    1.74
     After
    1.70
     ,
    1.70
     Life
    1.68
     This
    1.67
    ầy
    1.66
    )
    1.66
    POSITIVE LOGITS
    ymmetrical
    2.70
    itano
    2.67
    िना
    2.66
    АТО
    2.65
    მასრულ
    2.62
    utth
    2.58
    akana
    2.57
    ఆడిన
    2.56
    路撒
    2.53
    arote
    2.53
    Activations Density 0.000%

    No Known Activations