© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129778
    Prev
    Next
    INDEX
    Explanations

    otter, error handling, paramilitary, combinations

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

    The neuron activates on occurrences of the string “otter” (e.g. in “Otter,” “OtterBox,” or similar).

    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
    𐐪
    -2.42
    鼉
    -2.39
    吶
    -2.31
     ayakkab
    -2.27
    ارتمان
    -2.23
     ennemi
    -2.22
    𝔗
    -2.17
     ayakkabı
    -2.14
    繾
    -2.13
    𝕿
    -2.09
    POSITIVE LOGITS
     ‘
    2.72
    1
    2.69
    </strong>
    2.67
    \
    2.56
             
    2.55
     ‘‘
    2.55
    ’,
    2.55
        
    2.53
          
    2.52
                    
    2.48
    Activations Density 0.001%

    No Known Activations