© 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. 241011
    Prev
    Next
    INDEX
    Explanations

    bonus operating income

    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
    Million
    0.50
    orth
    0.49
    $-$
    0.47
    س
    0.47
    ${
    0.47
     等
    0.47
    $\
    0.46
    非常
    0.46
    Karnataka
    0.46
    6
    0.46
    POSITIVE LOGITS
     harán
    0.55
     senjata
    0.54
     অস্ত্র
    0.50
     puertos
    0.50
    apkan
    0.47
     básicas
    0.47
    zelfde
    0.47
    áculo
    0.47
     besi
    0.47
     çöze
    0.46
    Activations Density 0.000%

    No Known Activations