© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39089
    Prev
    Next
    INDEX
    Explanations

    powering electric systems

    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
     to
    -1.90
    t
    -1.14
    “
    -1.13
    ''
    -1.11
     there
    -1.09
    '
    -1.05
    s
    -1.04
    ائل
    -1.02
    _
    -1.02
     spørs
    -1.02
    POSITIVE LOGITS
     our
    1.62
    𖧵
    1.44
     trám
    1.41
    周泽
    1.35
    鸶
    1.34
     наших
    1.32
    
    1.31
    Chúng
    1.30
     alcune
    1.25
    Bước
    1.24
    Activations Density 0.057%

    No Known Activations