© 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. 10-GEMMASCOPE-RES-131K
    7. 38710
    Prev
    Next
    INDEX
    Explanations

    vibrations and oscillations

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

    The neuron responds to terms describing oscillation or periodic oscillatory behavior.

    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
     dallo
    -1.84
     esigen
    -1.80
     vettore
    -1.76
     autunno
    -1.65
     Those
    -1.64
    也是
    -1.59
     visione
    -1.59
     canali
    -1.53
     mobilité
    -1.52
    pperware
    -1.52
    POSITIVE LOGITS
     conseguir
    1.67
    𓋼
    1.61
    leyin
    1.55
     sorgen
    1.52
     türk
    1.46
    denn
    1.45
    
    1.45
    ция
    1.44
     лучшие
    1.44
     $
    1.43
    Activations Density 0.087%

    No Known Activations