© 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. 31627
    Prev
    Next
    INDEX
    Explanations

    impedance, dynamic, thermal, AC frequency

    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
    NSU
    -0.71
    峠
    -0.69
    FileUtil
    -0.69
    级
    -0.68
     ELE
    -0.68
     rectal
    -0.68
     Endor
    -0.67
    RATES
    -0.67
     Manner
    -0.66
    LOU
    -0.65
    POSITIVE LOGITS
     lock
    0.86
     signal
    0.81
    gapan
    0.79
    Lock
    0.78
    signal
    0.74
     frequencies
    0.73
     frequency
    0.72
     AC
    0.72
    Frequency
    0.71
     Frequency
    0.70
    Activations Density 0.041%

    No Known Activations