© 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. 13713
    Prev
    Next
    INDEX
    Explanations

    "now" followed by place names

    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
     в
    1.86
     вниз
    1.86
    к
    1.84
     ช
    1.79
     بم
    1.77
     เกี่ยว
    1.76
     ถ
    1.73
    traj
    1.72
    thickness
    1.70
     часто
    1.68
    POSITIVE LOGITS
     automatis
    1.54
    눙
    1.53
    瓈
    1.53
    냔
    1.51
    να
    1.50
     unseren
    1.49
     unserer
    1.48
     dieser
    1.47
     halb
    1.45
    ේව
    1.45
    Activations Density 0.022%

    No Known Activations