© 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. 27679
    Prev
    Next
    INDEX
    Explanations

    descriptive qualifiers

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

    CPU, frequency, resource management

    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
    㑓
    0.55
     Тогда
    0.53
     PackageManager
    0.53
     След
    0.53
     России
    0.52
     输出
    0.52
    MSFontService
    0.51
     Tattha
    0.51
     昨日
    0.51
     войны
    0.50
    POSITIVE LOGITS
    al
    0.58
    3
    0.51
     financieras
    0.48
    nucle
    0.48
     sandpaper
    0.46
     nucle
    0.46
    ITS
    0.46
    itur
    0.45
    STITUTION
    0.44
     compare
    0.44
    Activations Density 0.000%

    No Known Activations