© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105028
    Prev
    Next
    INDEX
    Explanations

    code and proper names

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

    the word "axios" and related HTTP request library usage in code.

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

    The neuron detects mentions of the Axios HTTP client (especially axios.get calls).

    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
     also
    -2.03
     where
    -1.99
     seems
    -1.82
     without
    -1.79
    ’
    -1.76
     amidst
    -1.73
     alongside
    -1.70
     with
    -1.69
     beberapa
    -1.65
     coupled
    -1.61
    POSITIVE LOGITS
    熜
    1.84
    莛
    1.70
     formules
    1.63
    瑒
    1.62
     fermer
    1.60
     tirer
    1.60
    业主
    1.59
     najleps
    1.57
     حين
    1.56
    ჻
    1.56
    Activations Density 0.005%

    No Known Activations