© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8825
    Prev
    Next
    INDEX
    Explanations

    programming code symbols

    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_22_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
    in
    0.84
     in
    0.82
     فول
    0.79
     Wrapped
    0.78
     الأخ
    0.77
     الور
    0.77
    ાળા
    0.76
    폴
    0.76
     واس
    0.75
     粉
    0.74
    POSITIVE LOGITS
     exponential
    1.08
     Mercado
    1.07
     garagem
    1.06
    checkout
    1.05
    marca
    1.04
    <unused1748>
    1.03
     psychology
    1.02
    zetac
    1.02
    <unused1223>
    1.02
     फार्मूला
    1.01
    Activations Density 0.001%

    No Known Activations