© 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. 103422
    Prev
    Next
    INDEX
    Explanations

    image file paths

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

    the token "img" in file paths and URLs, particularly when it appears before a forward slash.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on “img” and the following slash tokens in file‐path or URL contexts, i.e. it detects image file references.

    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
    A
    -1.84
    }
    -1.81
    </h1>
    -1.81
    ’
    -1.77
    {
    -1.71
    }
    -1.66
    C
    -1.66
    of
    -1.63
    <b>
    -1.62
    }\
    -1.61
    POSITIVE LOGITS
     dobrý
    2.13
     všem
    1.88
     bénéficiaire
    1.87
    が必要です
    1.79
     naší
    1.74
    
    1.74
     damski
    1.73
     savu
    1.73
    ܖ
    1.67
    ܞ
    1.61
    Activations Density 0.006%

    No Known Activations