© 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. 31919
    Prev
    Next
    INDEX
    Explanations

    election and legal outcomes

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

    Java date/time and stream collectors

    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
     صاح
    0.44
     टेंपरेचर
    0.42
     Ahmedabad
    0.41
    Baltimore
    0.41
     Prostate
    0.41
    螯
    0.41
    вла
    0.40
     prostat
    0.40
    麋
    0.40
    өт
    0.40
    POSITIVE LOGITS
     Yen
    0.47
    建
    0.45
    jdk
    0.44
    jsr
    0.43
    watch
    0.40
     watch
    0.40
    urf
    0.39
    λα
    0.39
    centos
    0.39
     Pacific
    0.38
    Activations Density 0.006%

    No Known Activations