© 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. 112193
    Prev
    Next
    INDEX
    Explanations

    common leading words

    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
    两年
    -1.51
    ,”
    -1.43
    !”
    -1.41
     –
    -1.35
    鲮
    -1.31
     calefacción
    -1.29
     soldadura
    -1.28
     Füßen
    -1.26
    髏
    -1.25
    ?”
    -1.24
    POSITIVE LOGITS
    '
    1.59
    to
    1.54
     TableColumn
    1.48
    clusions
    1.44
     armen
    1.43
    InputStream
    1.42
    To
    1.39
     果
    1.38
    ⁴
    1.38
    providedIn
    1.37
    Activations Density 0.005%

    No Known Activations