© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91168
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and environments

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

    The neuron selectively activates on integer tokens (i.e. standalone numbers) in the text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     );
    
    -0.90
    ']==
    -0.90
    providedIn
    -0.90
    ']);
    
    -0.86
     >=
    -0.86
    ]));
    -0.85
    になったら
    -0.85
    *}
    
    -0.85
     [];
    -0.84
    влечения
    -0.84
    POSITIVE LOGITS
    ↵
    1.27
    ✮
    0.89
    饰演
    0.87
     terrestre
    0.86
    éticas
    0.86
    too
    0.85
     perfecte
    0.84
     where
    0.83
    ceased
    0.82
     pò
    0.82
    Activations Density 0.013%

    No Known Activations