© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7501
    Prev
    Next
    INDEX
    Explanations

    Names in brackets

    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_13_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
     或
    2.09
     或者
    2.02
     啊
    2.02
     ឬ
    1.91
     怪
    1.88
     少し
    1.87
     조금
    1.85
     абсолютно
    1.84
     굉장히
    1.81
     ή
    1.80
    POSITIVE LOGITS
    the
    1.15
     the
    1.06
     Covid
    1.00
    vide
    0.97
    The
    0.96
    during
    0.95
     respective
    0.94
    COVID
    0.93
    Covid
    0.92
    financial
    0.92
    Activations Density 0.044%

    No Known Activations