© 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. 10-GEMMASCOPE-RES-131K
    7. 103575
    Prev
    Next
    INDEX
    Explanations

    rich in substance

    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
    a
    -1.94
     “
    -1.91
    </h5>
    -1.53
    t
    -1.47
    >_
    -1.45
     by
    -1.44
     ”
    -1.44
    an
    -1.43
    讥
    -1.41
    ...”
    -1.40
    POSITIVE LOGITS
    啊啊
    1.72
     sebag
    1.65
     lantaran
    1.61
    鼇
    1.60
     kalem
    1.59
     denaro
    1.59
     opportunità
    1.57
     namun
    1.57
     apalagi
    1.53
     Namun
    1.52
    Activations Density 0.018%

    No Known Activations