© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1375
    Prev
    Next
    INDEX
    Explanations

    Pinterest search pins

    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
     이는
    2.58
    ゅ
    2.52
    s
    2.47
    sma
    2.40
    t
    2.34
    tidak
    2.28
    т
    2.24
    tare
    2.16
    了嗎
    2.16
    sion
    2.11
    POSITIVE LOGITS
    ավոր
    1.91
    aganda
    1.74
    araj
    1.71
    
    1.68
     vocabulary
    1.68
    ete
    1.62
    endtime
    1.61
    unciation
    1.57
    hash
    1.53
    ology
    1.53
    Activations Density 0.048%

    No Known Activations