© 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. 16284
    Prev
    Next
    INDEX
    Explanations

    artificial neural network methods

    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
    Suka
    -1.35
     ecuator
    -1.25
    criminate
    -1.22
    bezpiecz
    -1.19
    zestaw
    -1.15
     anhänger
    -1.09
    depends
    -1.09
     congrès
    -1.08
    Sergey
    -1.07
    ilustrasi
    -1.05
    POSITIVE LOGITS
     approach
    1.29
    将其
    1.11
     help
    1.09
    ^{}
    1.06
    の一
    1.05
    ช่วย
    1.05
     tidigare
    1.02
     method
    0.99
     förra
    0.99
     deutschland
    0.98
    Activations Density 0.163%

    No Known Activations