© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14729
    Prev
    Next
    INDEX
    Explanations

    silent, silence, quiet

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

    silence and quiet states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laz
    0.59
     relaxing
    0.56
     (
    0.53
     soothing
    0.53
     in
    0.53
     lazy
    0.52
     Relax
    0.52
     anchors
    0.51
     –
    0.51
    <b>
    0.50
    POSITIVE LOGITS
    Silent
    1.05
     silenc
    0.95
     Silent
    0.94
    silent
    0.93
     silent
    0.91
    Silence
    0.90
     silencio
    0.89
     silenz
    0.86
    沉默
    0.84
     चुप्पी
    0.82
    Activations Density 0.066%

    No Known Activations