© 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. 75544
    Prev
    Next
    INDEX
    Explanations

    holders choose

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

    "striking visual", "your patience", "unique", "Detection", "automate"

    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
    บ
    0.49
    ة
    0.49
    樂
    0.48
    AK
    0.47
    铠
    0.47
    嗨
    0.46
    北方
    0.46
    旅
    0.46
    人格
    0.45
    ა
    0.45
    POSITIVE LOGITS
     imagining
    0.52
    s
    0.52
     mengingat
    0.49
    surf
    0.45
    holes
    0.43
    has
    0.43
     Freed
    0.42
     sandstone
    0.42
    sellers
    0.42
     pneumonia
    0.41
    Activations Density 0.000%

    No Known Activations