© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113349
    Prev
    Next
    INDEX
    Explanations

    Vanessa and Firefox

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

    the name "Vanessa" or software names like "Firefox".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is primarily detecting the proper name “Vanessa.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    section
    -2.72
    </b>
    -2.70
    In
    -2.52
    u
    -2.41
    </
    -2.39
    .”
    -2.33
    </h4>
    -2.31
    伃
    -2.31
     It
    -2.31
    2
    -2.23
    POSITIVE LOGITS
    ↵↵
    2.97
    ."));
    2.94
    摀
    2.36
    Править
    2.31
    下意识
    2.25
    …).
    2.22
    )";
    
    2.17
    […]
    2.16
    toward
    2.13
    :“……”
    2.11
    Activations Density 0.005%

    No Known Activations