© 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. 22-GEMMASCOPE-2-RES-16K
    4. 10381
    Prev
    Next
    INDEX
    Explanations

    Text HOME to 741741

    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>
    3.94
    ↵↵
    3.11
    <h2>
    2.51
    <eos>
    2.44
    <h3>
    2.19
    ↵↵↵↵
    2.02
    ↵↵↵
    1.91
    ↵↵↵↵↵
    1.67
    ↵↵↵↵↵↵↵↵
    1.65
    <strong>
    1.65
    POSITIVE LOGITS
    </i>
    3.09
    </em>
    2.78
    $.}
    2.34
    </u>
    2.22
    …]
    2.09
    ...]
    2.09
    </s>
    2.04
     ...]
    2.02
    </sup>
    1.98
    .].
    1.96
    Activations Density 0.013%

    No Known Activations