© 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. 113360
    Prev
    Next
    INDEX
    Explanations

    html/xml tags like bold

    np_acts-logits-general · gemini-2.5-flash-lite

    HTML or XML tags, particularly opening tags like `<b>` and `<`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ).
    -1.94
    蛧
    -1.58
    ↵↵
    -1.52
    <strong>
    -1.47
    どっち
    -1.41
    ()
    -1.40
    两种
    -1.36
     n
    -1.36
     excitedly
    -1.36
     o
    -1.34
    POSITIVE LOGITS
     savons
    1.71
     bénéficier
    1.67
     serons
    1.59
    嫑
    1.55
     炖
    1.53
     ſou
    1.51
    疃
    1.41
     procéder
    1.40
     diminuer
    1.39
     fermer
    1.38
    Activations Density 0.001%

    No Known Activations