© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2359
    Prev
    Next
    INDEX
    Explanations

    document pages

    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
     decrease
    1.10
     increase
    1.07
     balloons
    1.02
     payments
    1.01
    /−
    1.00
     bump
    0.97
     compensation
    0.94
     R
    0.93
     payment
    0.92
     atmospheric
    0.91
    POSITIVE LOGITS
     koos
    1.54
     shumë
    1.52
     dialogo
    1.46
     macht
    1.44
     világ
    1.43
     krás
    1.42
     velmi
    1.42
     bastante
    1.42
     dvoj
    1.42
     filosof
    1.42
    Activations Density 0.128%

    No Known Activations