© 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. 101111
    Prev
    Next
    INDEX
    Explanations

    code paths and filenames

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

    closing HTML or PHP tags, particularly `</td>` and file path separators in code.

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

    This neuron detects floating-point number literals (decimal 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_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
    :
    -2.22
    -,
    -2.02
    }
    -1.90
    -.
    -1.88
    却是
    -1.88
    fe
    -1.84
    -
    -1.82
     ruft
    -1.80
    "
    -1.80
    ve
    -1.78
    POSITIVE LOGITS
     Begleitung
    1.98
     Ankunft
    1.89
     cráneo
    1.82
     estímulo
    1.81
     atractiva
    1.80
     aliado
    1.80
     Unterscheidung
    1.78
    羕
    1.77
     geringen
    1.77
     Vielfalt
    1.77
    Activations Density 0.001%

    No Known Activations