© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84332
    Prev
    Next
    INDEX
    Explanations

    quantitate or endblock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -2.38
    e
    -2.23
     Некоторые
    -2.23
    可能会
    -2.13
    IBLE
    -2.09
    ↵
    -2.08
     stupe
    -2.06
    er
    -2.03
    べし
    -1.99
    hpur
    -1.98
    POSITIVE LOGITS
     are
    2.63
     ‚
    2.61
    乆
    2.56
     Käufer
    2.44
    \
    2.42
    ㌘
    2.41
     لون
    2.25
     negozi
    2.20
     liquido
    2.16
    就是
    2.11
    Activations Density 0.001%

    No Known Activations