© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    vibration and oscillation dynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     olor
    -0.81
    vertis
    -0.78
     шла
    -0.72
     السياس
    -0.71
    Deviation
    -0.70
    ELO
    -0.70
     legion
    -0.68
    shot
    -0.66
    grained
    -0.66
     RCP
    -0.66
    POSITIVE LOGITS
     shaker
    1.23
     excitation
    1.15
     excited
    1.11
    excitation
    1.08
     excites
    1.08
    DOF
    1.05
     shake
    1.00
     shaking
    0.99
     recept
    0.93
     Vibration
    0.91
    Activations Density 0.038%

    No Known Activations