© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111892
    Prev
    Next
    INDEX
    Explanations

    Proteolytic activity

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

    animal names, particularly "coyote" and other species names ending with "-ote" or "-otes".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on low‐frequency, specialized tokens (e.g. uncommon proper nouns and scientific terms).

    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
    </em>
    -2.83
    跸
    -2.27
    1
    -2.11
     excite
    -2.09
    ствуют
    -2.08
    豨
    -2.06
     divertidas
    -2.03
     anderen
    -2.02
     effec
    -2.00
     cihaz
    -2.00
    POSITIVE LOGITS
     "}";
    2.39
    </h1>
    2.05
    (…)
    1.94
    塤
    1.90
    </th>
    1.84
    ூர்
    1.84
    籐
    1.83
    滂
    1.81
    ❤
    1.80
    ן
    1.79
    Activations Density 0.007%

    No Known Activations