© 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. 8155
    Prev
    Next
    INDEX
    Explanations

    code, locations, names, science

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

    The neuron activates on capitalized tokens—proper names or code identifiers (e.g. class/method names in camel­Case or Pascal­Case).

    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
    {
    -2.88
    垕
    -2.06
     salieron
    -2.02
    。『
    -2.02
    蘩
    -1.98
     lutar
    -1.98
    垆
    -1.96
    薔薇
    -1.94
    灕
    -1.87
    独特
    -1.86
    POSITIVE LOGITS
    }$
    3.69
    e
    3.06
    
    2.56
    </th>
    2.31
    as
    2.27
    или
    2.22
    ឵
    2.22
    K
    2.19
    lietta
    2.19
    .”
    2.19
    Activations Density 0.000%

    No Known Activations