© 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. 13268
    Prev
    Next
    INDEX
    Explanations

    naked person identifier

    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
    i
    3.50
    es
    3.05
    oons
    2.95
    aes
    2.85
    o
    2.76
    िवा
    2.76
    る
    2.76
    a
    2.71
    ي
    2.67
     ​​​​
    2.61
    POSITIVE LOGITS
    zną
    2.93
    ্স
    2.55
    irmek
    2.46
    sthrough
    2.44
    than
    2.42
    uttle
    2.40
    coln
    2.40
    stitute
    2.39
    maja
    2.37
    sson
    2.33
    Activations Density 0.007%

    No Known Activations