© 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. 2072
    Prev
    Next
    INDEX
    Explanations

    key to improvements

    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
    s
    3.06
     ArrayAdapter
    2.91
     Hardly
    2.91
    sı
    2.85
     ㅏ
    2.84
    ዐይን
    2.81
     यकीन
    2.78
     gacche
    2.75
    ATION
    2.75
    BeanFactory
    2.72
    POSITIVE LOGITS
    ील
    2.30
    hibit
    2.16
    링
    2.05
     short
    2.05
    كز
    2.04
     trace
    2.04
     long
    2.02
     shorter
    2.02
    от
    2.00
    hole
    2.00
    Activations Density 0.028%

    No Known Activations