© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199240
    Prev
    Next
    INDEX
    Explanations

    Soundproof Window Guys

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

    continuous flow, flu, common, mini, regulation

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    preet
    0.47
    ൊ
    0.46
     facilite
    0.46
    ጋገብ
    0.45
    чает
    0.44
    지난
    0.44
    Hair
    0.43
    voer
    0.42
    돼
    0.42
     vestiges
    0.42
    POSITIVE LOGITS
     Uyg
    0.54
    át
    0.48
    ết
    0.48
     गिरने
    0.44
    ucin
    0.43
    ématiques
    0.43
    platten
    0.41
    μαν
    0.41
     осмо
    0.41
    éné
    0.40
    Activations Density 0.000%

    No Known Activations