© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79353
    Prev
    Next
    INDEX
    Explanations

    license text and versions

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

    The neuron fires on boilerplate license‐header markers—i.e. the boundaries and identifiers (like “Mozilla Public License,” version blocks, etc.) that denote the start of a license section.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ugos
    -0.90
    bridal
    -0.86
    boite
    -0.85
     actionTypes
    -0.84
     berikutnya
    -0.84
     $)
    -0.83
    Objec
    -0.82
    scry
    -0.82
     adorno
    -0.82
    blouse
    -0.82
    POSITIVE LOGITS
    jenige
    0.95
    SequentialGroup
    0.89
     Bedürfnisse
    0.88
    Sho
    0.87
    なんですね
    0.85
    噹
    0.84
    MB
    0.83
    CONTENT
    0.82
     fever
    0.81
    AddHtmlAttribute
    0.81
    Activations Density 0.000%

    No Known Activations