© 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. 7-GEMMASCOPE-2-RES-16K
    7. 110
    Prev
    Next
    INDEX
    Explanations

    measurable outcomes

    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_7_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
    r
    2.13
    ang
    2.02
    its
    1.87
    bot
    1.80
    ì
    1.80
    ӯ
    1.74
    ib
    1.74
    R
    1.73
    inia
    1.72
    rr
    1.66
    POSITIVE LOGITS
    𝘩
    2.87
     recourse
    2.65
    कतों
    2.64
     avuto
    2.64
     پیشن
    2.63
    𝘻
    2.62
    ্ত্র
    2.57
    ारीरिक
    2.56
    𝘥
    2.55
    xcodep
    2.51
    Activations Density 1.460%

    No Known Activations