© 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. 12221
    Prev
    Next
    INDEX
    Explanations

    programming terms and prepositions

    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
    en
    2.80
    edes
    2.55
    जूदा
    2.31
    𝑡
    2.30
     zakl
    2.29
    𝑖
    2.27
     hObject
    2.20
    enas
    2.16
    canny
    2.15
    aginaw
    2.15
    POSITIVE LOGITS
    ...*/
    4.23
    #__
    3.34
    োধী
    2.79
    }*/
    2.68
     eser
    2.50
    ඈ
    2.48
    ्तीय
    2.42
    house
    2.40
    Ḵ
    2.38
     बढ़ावा
    2.37
    Activations Density 0.000%

    No Known Activations