© 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. 10-GEMMASCOPE-RES-131K
    7. 102832
    Prev
    Next
    INDEX
    Explanations

    analytical variation

    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_10/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
     it
    -3.64
     and
    -3.05
     have
    -2.97
     there
    -2.58
     should
    -2.41
     you
    -2.22
     during
    -1.95
     get
    -1.87
     this
    -1.83
    there
    -1.83
    POSITIVE LOGITS
     mág
    1.88
    nother
    1.85
    mbal
    1.83
    蟥
    1.80
     jei
    1.80
     BitSet
    1.80
     matem
    1.80
     elegante
    1.79
     idiota
    1.78
     PyLong
    1.77
    Activations Density 0.233%

    No Known Activations