© 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. 10302
    Prev
    Next
    INDEX
    Explanations

    goals and timelines

    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
    <start_of_image>
    1.53
    <strong>
    1.21
      
    0.89
    </strong>
    0.84
    】，
    0.82
     usted
    0.82
     фонбет
    0.82
    你就
    0.80
    你的
    0.80
            
    0.78
    POSITIVE LOGITS
    </i>
    2.25
    </h6>
    1.53
     阅读全文
    1.39
    </code>
    1.35
     ⠀
    1.34
    </s>
    1.27
    .""
    1.27
    〗
    1.24
     (...
    1.20
    </h1>
    1.19
    Activations Density 0.118%

    No Known Activations