© 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. 243939
    Prev
    Next
    INDEX
    Explanations

    occasional partners

    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
     nejen
    0.44
     remnant
    0.40
     Chauhan
    0.40
    ራ
    0.39
    早就
    0.39
     měla
    0.39
     Jerez
    0.39
     Iglesia
    0.38
     believed
    0.38
     Canaan
    0.38
    POSITIVE LOGITS
     qualche
    0.47
     occasionally
    0.46
     QSOs
    0.42
    \\.
    0.42
     någon
    0.42
     Occasionally
    0.41
     চিত্রক
    0.40
    /
    0.40
     algún
    0.40
     nogen
    0.40
    Activations Density 0.001%

    No Known Activations