© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41431
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     sapat
    -1.89
    猡
    -1.62
     moldura
    -1.60
     makita
    -1.54
     recev
    -1.48
     when
    -1.48
     bascul
    -1.48
    戇
    -1.48
     brisa
    -1.48
     colch
    -1.46
    POSITIVE LOGITS
     of
    2.52
    This
    1.67
    These
    1.59
    ?"
    1.57
    都不是
    1.54
     รวม
    1.53
    на
    1.51
     ),
    1.44
     ).
    1.44
     этих
    1.39
    Activations Density 0.015%

    No Known Activations