© 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. 3529
    Prev
    Next
    INDEX
    Explanations

    vulnerable women

    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
    ọt
    2.46
    주의
    2.24
    ITÉ
    2.20
     fork
    2.16
    requis
    2.13
     βο
    2.11
     missing
    2.10
    눔
    2.10
    missing
    2.10
    bsen
    2.09
    POSITIVE LOGITS
    আর
    3.16
     Mustafa
    3.03
     Muham
    3.00
    iyat
    2.98
    iyah
    2.97
     Syed
    2.85
     અ
    2.84
    ޢ
    2.81
     Mosque
    2.74
     Muhammed
    2.73
    Activations Density 0.365%

    No Known Activations