© 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. 34-GEMMASCOPE-RES-131K
    7. 91621
    Prev
    Next
    INDEX
    Explanations

    questions or specific phrases

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

    The neuron strongly activates on mathematical notation and technical terms (especially LaTeX‐style expressions) such as “Optimization,” “Gradient,” “log,” “det,” “X,” and related math tokens.

    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
    OSSARY
    -0.74
     darling
    -0.66
    Superficie
    -0.65
     ponds
    -0.65
    فسير
    -0.65
     Ethyl
    -0.65
    rsquo
    -0.64
    Tink
    -0.64
     directory
    -0.64
     tax
    -0.64
    POSITIVE LOGITS
    sdp
    1.11
     Boyd
    1.03
    SDP
    1.00
    Boyd
    0.98
     SDP
    0.93
    PSD
    0.89
     psd
    0.85
    slack
    0.84
    psd
    0.84
     DCP
    0.83
    Activations Density 0.033%

    No Known Activations