© 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. 113538
    Prev
    Next
    INDEX
    Explanations

    questionnaire administration and investigation

    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
     was
    -2.58
    
    -2.47
     aching
    -2.47
    咴
    -2.39
    تیجه
    -2.39
    ۺ
    -2.36
     市场
    -2.33
     admon
    -2.31
     infused
    -2.23
     demonstra
    -2.22
    POSITIVE LOGITS
    al
    3.02
    </h3>
    2.42
    <bos>
    2.42
    '
    2.36
    to
    2.20
    “
    2.14
     
    2.13
     abbiano
    2.06
    比如说
    1.97
    </strong>
    1.95
    Activations Density 0.006%

    No Known Activations