© 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. 86173
    Prev
    Next
    INDEX
    Explanations

    asking 'whats'

    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
     広場
    -2.59
    “
    -2.38
     mutiara
    -2.34
    硨
    -2.34
    unggah
    -2.17
     flink
    -2.17
    НОГО
    -2.16
     cascades
    -2.11
     mence
    -2.11
     jepang
    -2.09
    POSITIVE LOGITS
    }$.
    2.69
    ↵↵
    2.39
     t
    2.28
     u
    2.23
     whats
    2.11
    到现在
    2.09
    ();
    2.08
     n
    2.03
    ｰ
    1.94
     It
    1.93
    Activations Density 0.003%

    No Known Activations