© 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. 112654
    Prev
    Next
    INDEX
    Explanations

    District of Columbia, commissioners, Supervisors

    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
    
    -1.80
    guantes
    -1.63
     militaires
    -1.52
    蓐
    -1.52
    〢
    -1.48
     französ
    -1.46
     fossero
    -1.44
     münchen
    -1.44
     márm
    -1.43
     damal
    -1.41
    POSITIVE LOGITS
     in
    1.86
    ing
    1.76
     has
    1.61
    if
    1.60
     with
    1.56
     to
    1.47
    在我
    1.41
    </b>
    1.41
     or
    1.41
    }\
    1.38
    Activations Density 0.253%

    No Known Activations