© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14305
    Prev
    Next
    INDEX
    Explanations

    Draws Gizmos

    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
    ↵
    1.87
     sensibil
    1.22
     Cape
    1.18
     Storm
    1.16
    小
    1.16
    ää
    1.09
     informations
    1.09
     lectures
    1.09
     Londres
    1.08
     fred
    1.07
    POSITIVE LOGITS
     Bxa
    1.93
    dtype
    1.81
    右手
    1.78
    зит
    1.75
    <unused1783>
    1.75
    '{
    1.75
    İL
    1.72
    itm
    1.71
    bati
    1.70
    cón
    1.69
    Activations Density 0.002%

    No Known Activations