© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6871
    Prev
    Next
    INDEX
    Explanations

    domestic violence hotline and NIH

    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_22_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
     estre
    0.92
    Than
    0.88
    劳
    0.85
     Kirkland
    0.85
     anatomical
    0.84
     Aubrey
    0.83
     anatomy
    0.82
    勞
    0.81
     Orlando
    0.81
     stato
    0.81
    POSITIVE LOGITS
    queline
    0.97
     знаю
    0.95
     learnt
    0.88
    wohl
    0.85
    IME
    0.85
    勉強
    0.84
     wiem
    0.83
    QUARE
    0.82
    짜
    0.82
     понимаю
    0.81
    Activations Density 0.055%

    No Known Activations