© 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. 12410
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    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
    िना
    2.12
    𝑣
    2.05
     pouv
    2.03
    ѵ
    2.02
     aritmética
    1.90
     máxima
    1.89
     vě
    1.82
     chiaro
    1.82
    𝑡
    1.81
    粈
    1.79
    POSITIVE LOGITS
     中
    2.06
     인수
    1.93
     근
    1.91
    Ein
    1.80
     반
    1.77
    Tong
    1.75
     식
    1.75
    ishi
    1.71
     느
    1.70
     골
    1.70
    Activations Density 0.263%

    No Known Activations