© 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. 49318
    Prev
    Next
    INDEX
    Explanations

    accumulated resources, stored data

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

    resources used or allocated

    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
    sschutz
    0.56
    password
    0.52
    woocommerce
    0.50
     nightlife
    0.49
     అర్జు
    0.49
    无穷
    0.48
     تحلیل
    0.48
    =>{
    0.47
    အစိတ်အပိုင်း
    0.47
    管理员
    0.47
    POSITIVE LOGITS
     mustered
    0.39
    enses
    0.38
     tightly
    0.38
     contaminating
    0.38
    iteracy
    0.37
    Responses
    0.37
    대는
    0.37
     systems
    0.37
    Systems
    0.36
     Systems
    0.36
    Activations Density 0.000%

    No Known Activations