© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16202
    Prev
    Next
    INDEX
    Explanations

    magnitude followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    葯
    -1.08
     그것
    -1.06
     좋은
    -1.05
     also
    -1.05
    作品の
    -1.04
    齟
    -1.00
     屏
    -0.99
    …？
    -0.99
     스톡
    -0.98
     이야
    -0.98
    POSITIVE LOGITS
     or
    1.63
     eller
    1.32
     alebo
    1.14
     laiss
    1.10
     или
    1.04
    或
    1.03
    (?)
    1.02
    の基本
    0.98
    áklad
    0.98
     horen
    0.98
    Activations Density 0.222%

    No Known Activations