© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31154
    Prev
    Next
    INDEX
    Explanations

    getting list items

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

    The neuron primarily detects numeric tokens (literal 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
     isn
    -0.89
    FirstOrDefault
    -0.85
     marshes
    -0.84
    īgā
    -0.82
     first
    -0.79
     wasn
    -0.79
    getNome
    -0.79
    笙
    -0.78
    éo
    -0.77
    Evans
    -0.77
    POSITIVE LOGITS
    querySelectorAll
    1.27
    的所有
    1.14
     getAll
    1.11
    getAll
    1.09
    GetAll
    1.05
    ToArray
    1.03
    readlines
    1.02
     GetAll
    1.02
    NSArray
    0.99
     목록
    0.98
    Activations Density 0.033%

    No Known Activations