© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6008
    Prev
    Next
    INDEX
    Explanations

    oldest, better, most

    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_13_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
    /
    1.11
     وش
    1.10
    👌
    1.09
     وتم
    1.09
     وف
    1.07
    وف
    1.06
     وتح
    1.03
    /"
    1.03
    Мі
    1.03
    -/
    1.02
    POSITIVE LOGITS
     electrician
    1.12
     busiest
    1.10
     franchisee
    1.09
    aconit
    1.09
     teammate
    1.08
    akta
    1.08
     actually
    1.06
     franchisees
    1.05
     ভোর
    1.04
     Tans
    1.03
    Activations Density 0.000%

    No Known Activations