© 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. 208015
    Prev
    Next
    INDEX
    Explanations

    crashing medical stunning mountain town

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

    least privilege access

    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
    鴿
    0.50
     Round
    0.44
     Involved
    0.43
     Supporting
    0.43
    祛
    0.42
    avir
    0.42
     Facing
    0.42
     Nomenclature
    0.41
    িপুর
    0.41
    嚧
    0.41
    POSITIVE LOGITS
     execution
    0.50
     turbines
    0.50
     rockets
    0.48
     decrees
    0.47
     detonations
    0.47
     duties
    0.47
     supersymmetry
    0.46
     executed
    0.46
     rightful
    0.45
    นาย
    0.45
    Activations Density 0.001%

    No Known Activations