© 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. 9508
    Prev
    Next
    INDEX
    Explanations

    CON followed by other letters

    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
    '
    -2.50
    僭
    -2.36
     Not
    -2.34
    鈑
    -2.23
     Even
    -2.22
     To
    -2.19
    Skocz
    -2.17
    蕓
    -2.17
    â
    -2.16
    孰
    -2.16
    POSITIVE LOGITS
    鮡
    3.20
    a
    3.11
    ”
    2.75
    ܆
    2.64
    都没
    2.63
    盉
    2.63
    趿
    2.58
    ÕES
    2.52
    艫
    2.52
     enregistrer
    2.48
    Activations Density 0.006%

    No Known Activations