© 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. 14151
    Prev
    Next
    INDEX
    Explanations

    anonymous function

    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
    ेक्षित
    3.35
    ेक्षा
    3.14
    NotNull
    2.86
    ธุ์
    2.85
    ллі
    2.84
    ጴ
    2.82
    ܢܐ
    2.80
    トゥーン
    2.77
    রাষ্ট
    2.76
    zeko
    2.74
    POSITIVE LOGITS
     clim
    2.09
    Ụ
    2.02
     hearth
    2.00
     hung
    2.00
     justice
    1.98
    ovor
    1.91
    Scal
    1.87
     hang
    1.85
     bel
    1.83
    </blockquote>
    1.81
    Activations Density 0.013%

    No Known Activations