© 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. 1475
    Prev
    Next
    INDEX
    Explanations

    domestic violence, Mercedes-Benz, conscious

    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
     â
    1.88
    â
    1.85
     The
    1.76
     скоро
    1.76
     corner
    1.75
     damn
    1.69
    2
    1.69
     car
    1.69
     cant
    1.66
    The
    1.65
    POSITIVE LOGITS
    峹
    3.48
    ㇇
    3.31
    㳡
    3.22
    맇
    3.04
    𝐨
    2.98
    곞
    2.95
    冖
    2.95
    퍁
    2.94
     한다
    2.93
    kepsilon
    2.92
    Activations Density 1.438%

    No Known Activations