© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109941
    Prev
    Next
    INDEX
    Explanations

    conditional phrases

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

    offers several benefits

    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
     be
    0.54
    기
    0.50
    ل
    0.49
    ನ
    0.49
    지난
    0.47
     충분
    0.46
     그의
    0.46
    아
    0.46
     assass
    0.45
    ए
    0.45
    POSITIVE LOGITS
     券
    0.53
    lig
    0.49
    atief
    0.47
    untur
    0.47
    yscale
    0.44
     அதிசயங்கள்
    0.44
     exhibited
    0.44
     instituted
    0.43
     إلا
    0.43
    uldig
    0.43
    Activations Density 0.001%

    No Known Activations