© 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. 109605
    Prev
    Next
    INDEX
    Explanations

    signal bandwidth

    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
    amplitude
    -0.81
    Amplitude
    -0.75
     amplitude
    -0.73
    ፤
    -0.73
    Fornecedor
    -0.72
    aligned
    -0.71
    립
    -0.71
    filled
    -0.71
    дика
    -0.70
     заболе
    -0.69
    POSITIVE LOGITS
     bandwidth
    1.96
     cutoff
    1.63
    bandwidth
    1.58
     Bandwidth
    1.39
    cutoff
    1.30
    Bandwidth
    1.16
     BW
    1.10
    带宽
    1.07
    utoff
    1.05
     cut
    1.02
    Activations Density 0.064%

    No Known Activations