© 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. 10149
    Prev
    Next
    INDEX
    Explanations

    to acknowledge and offer support

    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
    STRAINT
    0.94
    担
    0.92
    נס
    0.91
    鯖
    0.88
     delaying
    0.88
    locked
    0.88
    dés
    0.88
     फा
    0.86
    logos
    0.86
    凍
    0.85
    POSITIVE LOGITS
    pperware
    1.55
    quoise
    1.13
    тю
    1.09
    bingen
    1.07
    ীব্র
    1.07
    erca
    1.04
    फान
    1.01
    fted
    1.00
    алет
    0.98
    lips
    0.98
    Activations Density 0.023%

    No Known Activations