© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81298
    Prev
    Next
    INDEX
    Explanations

    vibrational and variational spectroscopy

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

    scientific terms related to vibrational spectroscopy or analysis.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects occurrences of vibration-related terms (e.g. “vibration”, “vibrational,” “vibration-ally,” etc.).

    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
    бка
    -0.72
     configuração
    -0.70
    קרי
    -0.69
     Programmable
    -0.68
    ioare
    -0.66
    бки
    -0.66
    iência
    -0.65
     sonno
    -0.65
    izy
    -0.65
     sogen
    -0.65
    POSITIVE LOGITS
     Kore
    0.84
    état
    0.83
     شماره
    0.82
     cellule
    0.77
    EFE
    0.77
     quanta
    0.77
     insectic
    0.76
     anticoag
    0.75
     logos
    0.75
     mediana
    0.75
    Activations Density 0.044%

    No Known Activations