© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9065
    Prev
    Next
    INDEX
    Explanations

    consent and management

    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
     calculator
    1.23
    탉
    1.19
     friction
    1.18
     수학
    1.17
     fight
    1.17
    塙
    1.17
     motorcycle
    1.16
     jobSearch
    1.15
    芯
    1.15
     mathematician
    1.14
    POSITIVE LOGITS
    inci
    1.00
    గానే
    0.95
    ep
    0.94
    natal
    0.93
    ี้ยง
    0.89
     apoi
    0.88
    uen
    0.88
     Streams
    0.87
     โ
    0.87
    จำนวน
    0.86
    Activations Density 0.002%

    No Known Activations