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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91573
    Prev
    Next
    INDEX
    Explanations

    San Francisco

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

    defines or represents

    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
    Not in Any Lists

    No Comments

    Negative Logits
    </h2>
    0.28
     lanza
    0.27
     publie
    0.26
    </h3>
    0.25
     G
    0.25
     wicht
    0.25
    </h1>
    0.25
     ف
    0.24
    RUN
    0.24
    </strong>
    0.23
    POSITIVE LOGITS
    了一個
    0.28
    াতাড়ি
    0.28
     где
    0.28
    িয়াম
    0.27
    스러
    0.27
    feit
    0.27
    ভূম
    0.26
     ৬
    0.26
    ৬৫
    0.26
    
    0.26
    Activations Density 0.206%

    No Known Activations