© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9977
    Prev
    Next
    INDEX
    Explanations

    code snippets and syntax

    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_22_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
     Chestnut
    0.97
    setContent
    0.96
     beng
    0.94
     वेक्टर
    0.94
     ತುಂಬ
    0.94
    षेक
    0.93
     VAS
    0.92
    菱
    0.90
     короля
    0.90
    gahan
    0.89
    POSITIVE LOGITS
    <li>
    1.76
     LI
    1.61
    </ul>
    1.53
    li
    1.45
    LI
    1.42
    Li
    1.40
     Li
    1.38
     li
    1.37
     Lister
    1.17
    ลิ
    1.09
    Activations Density 0.022%

    No Known Activations