© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11905
    Prev
    Next
    INDEX
    Explanations

    registering actions or events

    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
    ১
    3.49
    ும்ப
    3.40
    ৭
    3.20
     gạo
    2.94
    这里
    2.87
    這裡
    2.86
    𝙜
    2.85
    anediyl
    2.85
     convoluted
    2.84
    énagement
    2.76
    POSITIVE LOGITS
    от
    3.14
    off
    2.84
    آور
    2.59
    احت
    2.49
    pik
    2.48
    OF
    2.44
    cesz
    2.41
    pace
    2.38
    قا
    2.37
    ﺍ
    2.33
    Activations Density 0.002%

    No Known Activations