© 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. 59329
    Prev
    Next
    INDEX
    Explanations

    cites EITHER

    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
    7
    -3.83
    6
    -3.77
    1
    -3.75
    8
    -3.67
    4
    -3.42
    9
    -3.41
    5
    -3.38
    3
    -3.28
    2
    -3.06
    All
    -2.56
    POSITIVE LOGITS
    傒
    2.31
    xiii
    2.28
     interessante
    2.20
     logiciels
    2.14
    ebbe
    2.11
    辚
    2.09
     “
    2.08
     the
    2.08
     ‘’
    2.08
     enorme
    2.06
    Activations Density 0.019%

    No Known Activations