© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10366
    Prev
    Next
    INDEX
    Explanations

    software components and agents

    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
    ämä
    1.06
     أو
    1.04
     المقدم
    1.03
    または
    1.02
    lair
    1.02
    omile
    1.00
     удосто
    1.00
    〒
    0.99
     обеспечения
    0.99
    Од
    0.99
    POSITIVE LOGITS
    !!!!!!!
    1.25
    !!!!!!
    1.23
    !!!!
    1.23
    !!!!!
    1.21
    !!!!!!!!
    1.21
    !!
    1.16
    !!!
    1.15
     !!!!
    1.09
     !!
    1.08
     huge
    1.08
    Activations Density 0.088%

    No Known Activations