© 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. 13-GEMMASCOPE-2-RES-16K
    4. 256
    Prev
    Next
    INDEX
    Explanations

    listing and continuation

    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
    <unused1896>
    1.28
     ivvu
    1.27
    𒋼
    1.24
    enamefont
    1.20
    녃
    1.19
    <unused98>
    1.19
    ꩮ
    1.18
     क़ुर्आन
    1.17
     प्लेलिस्ट
    1.16
    <unused1119>
    1.16
    POSITIVE LOGITS
    ↵
    1.22
    )
    1.14
    ↵↵
    1.11
    <h2>
    0.99
    •
    0.96
     و
    0.96
    ،
    0.91
    and
    0.90
    To
    0.90
    In
    0.90
    Activations Density 0.915%

    No Known Activations