© 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. 103720
    Prev
    Next
    INDEX
    Explanations

    tray and trey names

    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
     questionSearch
    -2.77
    俅
    -2.56
    赁
    -2.53
    蒹
    -2.48
     女人
    -2.44
    ઁ
    -2.38
    诓
    -2.38
    謦
    -2.34
    鲧
    -2.34
     \_
    -2.33
    POSITIVE LOGITS
    If
    2.42
    Ultimately
    2.31
    ちなみに
    2.23
    ?
    2.22
    It
    2.22
    Luckily
    2.19
    This
    2.19
    You
    2.17
     
    2.17
     cuarenta
    2.11
    Activations Density 0.001%

    No Known Activations