© 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. 119988
    Prev
    Next
    INDEX
    Explanations

    words starting with ex

    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
    </strong>
    -2.97
    </u>
    -2.80
    e
    -2.66
    </th>
    -2.56
      
    -2.52
          
    -2.48
    ?
    -2.28
    ):
    -2.22
    <i>
    -2.19
    辚
    -2.16
    POSITIVE LOGITS
    ୈ
    2.84
     bedeckt
    2.67
    Ꮵ
    2.66
    uminazione
    2.58
     espoir
    2.44
     ex
    2.41
    鶲
    2.36
    YECTO
    2.36
    巿
    2.34
    isierten
    2.33
    Activations Density 0.006%

    No Known Activations