© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112283
    Prev
    Next
    INDEX
    Explanations

    hex or mac address segments

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

    the two-letter sequence "ee" in code identifiers, URLs, and technical text.

    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
    _{
    -3.23
     is
    -3.08
    嫒
    -2.89
    -2.77
    a
    -2.70
     estekak
    -2.58
     become
    -2.55
     {
    -2.50
    迓
    -2.36
     to
    -2.34
    POSITIVE LOGITS
     It
    2.53
     klarer
    2.39
     soñ
    2.36
    Despite
    2.33
    ра
    2.33
    僅
    2.30
     يمكنك
    2.30
     komplette
    2.27
     pernikahan
    2.25
    During
    2.23
    Activations Density 0.007%

    No Known Activations