© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187241
    Prev
    Next
    INDEX
    Explanations

    referring to figures

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

    fragrant vibrant grace peel

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <0x0D>
    0.57
     laptop
    0.50
     ambulances
    0.50
    </h3>
    0.49
    ↵
    0.48
    </h2>
    0.48
     ambulance
    0.46
    </h4>
    0.45
     HAC
    0.43
    :'',
    0.43
    POSITIVE LOGITS
    ო
    0.49
    强者
    0.47
    ächst
    0.46
     Catalonia
    0.46
    ွင့်
    0.45
    ној
    0.45
    镌
    0.45
    ność
    0.44
    ющей
    0.44
    期间
    0.43
    Activations Density 0.000%

    No Known Activations