© 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. 11586
    Prev
    Next
    INDEX
    Explanations

    export financing and licenses

    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
     '*
    2.40
    ्युअल
    2.29
     '**
    2.20
    EventHandler
    2.14
    occupied
    2.13
    啡
    2.12
     ('
    2.10
     LaSalle
    2.01
    ྕ
    1.98
     '':
    1.97
    POSITIVE LOGITS
    ぺ
    2.07
    uxxxx
    2.05
    zeug
    2.02
    શા
    2.02
    zeugen
    2.02
    塞尔
    1.98
     veo
    1.97
    basicConfig
    1.97
    rodite
    1.95
     firm
    1.94
    Activations Density 0.010%

    No Known Activations