© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7171
    Prev
    Next
    INDEX
    Explanations

    limits their, initial outbreak, VW Transporter, doing business

    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
    auks
    0.83
    ệu
    0.81
    龜
    0.80
    ложение
    0.80
    龟
    0.80
    urtle
    0.80
    agascar
    0.79
    추
    0.77
    ленно
    0.76
    ော်
    0.76
    POSITIVE LOGITS
    Armed
    1.18
    coloured
    1.15
    Recorded
    1.08
    Ironically
    1.07
    Television
    1.06
    Instituto
    1.05
    colored
    1.04
     угро
    1.04
     relacionada
    1.04
    Xinhua
    1.04
    Activations Density 0.000%

    No Known Activations