© 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. 25950
    Prev
    Next
    INDEX
    Explanations

    signal processing, DSP

    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
     infeksi
    -0.72
     Inhibition
    -0.69
    買った
    -0.68
    чета
    -0.67
     establishing
    -0.66
     influencing
    -0.65
     cánh
    -0.65
     normalization
    -0.65
     проводить
    -0.65
     perpetually
    -0.64
    POSITIVE LOGITS
     Signal
    1.73
    Signal
    1.72
     signal
    1.65
    signal
    1.63
     signals
    1.45
     Signals
    1.44
    信号
    1.42
    signals
    1.37
     DSP
    1.30
    SIGNAL
    1.27
    Activations Density 0.037%

    No Known Activations