© 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. 10544
    Prev
    Next
    INDEX
    Explanations

    GPUs

    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
    '
    1.22
    fish
    1.17
    .
    1.13
    edo
    1.09
    -
    1.07
    iron
    1.05
    edom
    1.02
    etti
    1.00
    jed
    0.98
    atein
    0.96
    POSITIVE LOGITS
    
    1.82
     MyRegisterClass
    1.82
    
    1.72
     cổng
    1.71
     HUOBI
    1.69
     appBar
    1.69
     CharPtr
    1.69
    
    1.68
     vivienda
    1.67
     BSData
    1.66
    Activations Density 0.179%

    No Known Activations