© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 10235
    Prev
    Next
    INDEX
    Explanations

    specific level related

    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
     thirsty
    0.93
    ・
    0.90
    ・
    0.86
     exhausting
    0.84
     wonder
    0.84
     effectual
    0.82
     ・
    0.82
     -
    0.81
    aisesti
    0.81
    শ্যক
    0.80
    POSITIVE LOGITS
    caused
    1.40
    generated
    1.32
    spawn
    1.31
    proposed
    1.25
    引发
    1.20
     generated
    1.20
     engender
    1.20
     veroor
    1.18
    issued
    1.17
    obtained
    1.17
    Activations Density 0.078%

    No Known Activations