© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45310
    Prev
    Next
    INDEX
    Explanations

    names followed by titles or affiliations

    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
    ↵
    -4.00
     ”
    -3.17
    “
    -2.86
    er
    -2.83
     —
    -2.70
     attain
    -2.61
    S
    -2.58
     decide
    -2.55
     owe
    -2.55
    AN
    -2.52
    POSITIVE LOGITS
     kleding
    2.70
     avevano
    2.66
    ﮩ
    2.58
    鐿
    2.55
     Strukt
    2.53
     suaminya
    2.53
     poë
    2.50
     kapture
    2.50
     Diſ
    2.47
     børn
    2.45
    Activations Density 0.006%

    No Known Activations