© 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-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2676
    Prev
    Next
    INDEX
    Explanations

    closing quotes and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    </blockquote>
    2.17
    <blockquote>
    1.67
    .'</
    1.06
    </em>
    1.00
     继续访问
    0.96
    =?";
    0.95
    </s>
    0.94
     />';
    0.92
    .';
    0.91
    }`;
    0.89
    POSITIVE LOGITS
    ")
    3.78
     ")
    3.77
    »)
    3.64
    ”)
    3.60
    »).
    3.43
    ')
    3.41
    `)
    3.38
    ").
    3.37
    .")
    3.29
    .”)
    3.29
    Activations Density 0.167%

    No Known Activations