© 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. 153366
    Prev
    Next
    INDEX
    Explanations

    million ambulance, dumbbell

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

    daily profit calculation

    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
    ndet
    0.51
    NFL
    0.45
    ERCE
    0.44
    ॕ
    0.44
    ंसिल
    0.43
    𝗯
    0.43
     Verfü
    0.42
    eşit
    0.41
     Tees
    0.41
    ｹ
    0.41
    POSITIVE LOGITS
     oldValue
    0.43
     pastas
    0.42
    司
    0.41
    یسر
    0.40
     difficulté
    0.40
     السابق
    0.39
     monochrome
    0.39
    راجع
    0.38
     splendour
    0.38
     eerder
    0.38
    Activations Density 0.000%

    No Known Activations