© 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. 115471
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and descriptions

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

    discussing practical or casual

    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
    balances
    0.45
     هناك
    0.44
    enz
    0.44
     zásobníku
    0.42
     తెలిపారు
    0.42
    ↵↵
    0.42
     кількість
    0.42
     ско
    0.41
     комиссии
    0.40
     рекомендуется
    0.39
    POSITIVE LOGITS
    疋
    0.50
     pandemi
    0.47
    சிரிய
    0.45
     Leibn
    0.45
    صیل
    0.44
    बत
    0.44
     telep
    0.44
     Werke
    0.43
    −</
    0.43
    ளைஞ
    0.42
    Activations Density 0.001%

    No Known Activations