© 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. 17-GEMMASCOPE-2-RES-16K
    4. 2141
    Prev
    Next
    INDEX
    Explanations

    high + modifier

    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_17_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
     自分
    1.52
     `<=
    1.51
     Comparable
    1.51
    DeviceCompliance
    1.49
     كتساوي
    1.48
    >∕
    1.47
    रखाव
    1.46
     MODKEY
    1.46
     égales
    1.44
     CharPtr
    1.43
    POSITIVE LOGITS
     fin
    0.80
     s
    0.76
     ist
    0.75
     cant
    0.75
    ることができます
    0.75
     ,
    0.75
     hem
    0.73
    amp
    0.72
     &
    0.72
     juc
    0.71
    Activations Density 0.026%

    No Known Activations