© 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. 22-GEMMASCOPE-RES-131K
    7. 25568
    Prev
    Next
    INDEX
    Explanations

    exists, there is, also

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

    This neuron fires on parameter names (identifiers) in function/method declarations or documentation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    positivos
    -1.15
    お疲れ
    -1.13
     [];
    -1.06
     or
    -1.05
    ];
    -1.02
    所在地
    -1.01
    mesin
    -0.98
     nadru
    -0.98
    第六
    -0.98
     protagonisti
    -0.97
    POSITIVE LOGITS
    在意
    1.28
    婭
    1.27
    がある
    1.21
    <bos>
    1.21
     brosse
    1.18
    もある
    1.16
    があると
    1.13
    があり
    1.12
    もあります
    1.12
    ねー
    1.10
    Activations Density 0.001%

    No Known Activations