© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48800
    Prev
    Next
    INDEX
    Explanations

    uninterrupted peace and quiet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spä
    0.42
    佝
    0.41
    眄
    0.39
    ɟ
    0.36
     Limited
    0.36
    ély
    0.36
    ⴳ
    0.34
    ug
    0.34
    ́ng
    0.34
    廢
    0.34
    POSITIVE LOGITS
     uninterrupted
    0.86
     undisturbed
    0.80
     спокойно
    0.71
     peaceful
    0.67
     unobstructed
    0.66
     tranquil
    0.63
     peacefully
    0.63
     quieter
    0.63
     спокой
    0.62
     tranquillity
    0.62
    Activations Density 0.074%

    No Known Activations