© 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. 12832
    Prev
    Next
    INDEX
    Explanations

    HTML tags and technical terms

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

    The neuron activates on numeric tokens, especially floating-point numbers with decimal points.

    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
    -2.13
    4
    -1.88
     will
    -1.86
    7
    -1.85
    </em>
    -1.84
    6
    -1.68
     but
    -1.45
    1
    -1.41
    '
    -1.40
     做法
    -1.38
    POSITIVE LOGITS
    ↵
    1.60
     másik
    1.57
    kHz
    1.55
     cuadrada
    1.53
     extremamente
    1.51
    ∽
    1.50
     inicialmente
    1.50
    ynchrotron
    1.46
    名を
    1.45
     ebenfalls
    1.44
    Activations Density 0.000%

    No Known Activations