© 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. 34-GEMMASCOPE-RES-131K
    7. 91867
    Prev
    Next
    INDEX
    Explanations

    programming code and libraries

    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_34/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
     even
    -1.59
     what
    -1.50
     any
    -1.48
     innovative
    -1.37
     high
    -1.32
    !!!!!
    -1.26
    Even
    -1.23
     thinks
    -1.20
     tailored
    -1.20
    !!
    -1.19
    POSITIVE LOGITS
     ROBERT
    1.29
     ™
    1.28
    particularly
    1.20
    despite
    1.19
    有些不
    1.18
    ebly
    1.18
    primarily
    1.18
    注意事
    1.16
    もある
    1.16
    もちゃ
    1.16
    Activations Density 0.012%

    No Known Activations