© 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. 110010
    Prev
    Next
    INDEX
    Explanations

    christmas ornaments

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

    path in your

    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
    Not in Any Lists

    No Comments

    Negative Logits
     दिव्य
    0.52
     apa
    0.44
    透
    0.44
    लेन
    0.43
    }-$
    0.40
     drunkenness
    0.40
     capsule
    0.40
     conversaciones
    0.40
     ヨコハマ
    0.40
     flask
    0.40
    POSITIVE LOGITS
    ℃
    0.46
    🧱
    0.45
     hạ
    0.42
    ина
    0.40
    茏
    0.39
    嘶
    0.39
     সমাপ্ত
    0.38
     Locker
    0.38
     étages
    0.38
     Files
    0.37
    Activations Density 0.000%

    No Known Activations