© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15247
    Prev
    Next
    INDEX
    Explanations

    -

    np_acts-logits-general · gemini-2.5-flash-lite

    creative text generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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>
    0.55
    </i>
    0.50
    </b>
    0.44
    マックス
    0.44
    ellingen
    0.42
     ­
    0.40
    love
    0.40
    mym
    0.40
     love
    0.39
     cu
    0.38
    POSITIVE LOGITS
    <strong>
    0.74
    <em>
    0.52
    <code>
    0.46
     Señor
    0.43
     फरक
    0.41
     ஆண்டுகளாக
    0.41
    <h5>
    0.40
     वर्गीकृत
    0.40
    ನಿರ್
    0.40
     هيكون
    0.40
    Activations Density 0.011%

    No Known Activations