© 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-RES-65K
    7. 31143
    Prev
    Next
    INDEX
    Explanations

    God and divinity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    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
     élevées
    0.68
     élevés
    0.65
     auxqu
    0.63
    <unused594>
    0.61
     plufieurs
    0.60
     έχ
    0.60
    <unused368>
    0.60
    <unused1058>
    0.59
     élevée
    0.59
     unbeliev
    0.57
    POSITIVE LOGITS
    '
    0.77
     on
    0.73
     search
    0.62
    ק
    0.62
    ือ
    0.57
     and
    0.57
    ีย
    0.57
    ’
    0.55
     تعالیٰ
    0.54
    st
    0.54
    Activations Density 0.016%

    No Known Activations