© 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. 106803
    Prev
    Next
    INDEX
    Explanations

    temporal phases and periods

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

    The neuron activates on numeric values and quantitative measurements (e.g. numbers, units, and measurement-related 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
     Sasuke
    -0.88
     عظ
    -0.87
    Caixa
    -0.82
     nikah
    -0.81
    Ferien
    -0.81
    domada
    -0.80
    idah
    -0.80
     Scuola
    -0.79
     crossroads
    -0.79
     seasonal
    -0.79
    POSITIVE LOGITS
     late
    1.38
     Late
    1.03
     early
    0.95
     mid
    0.95
    Late
    0.87
    late
    0.85
     cred
    0.84
     stance
    0.84
     Early
    0.82
     позд
    0.79
    Activations Density 0.173%

    No Known Activations