© 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. 128685
    Prev
    Next
    INDEX
    Explanations

    runner-up or runners on base

    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
    u
    -2.78
    ”
    -2.73
    s
    -2.66
     was
    -2.61
    at
    -2.59
    z
    -2.55
    2
    -2.52
    1
    -2.45
    ay
    -2.36
    in
    -2.33
    POSITIVE LOGITS
     accessing
    2.73
    relenting
    2.56
     constituting
    2.52
    洐
    2.44
    瀘
    2.44
    秕
    2.42
     tijden
    2.41
    盦
    2.41
    滹
    2.39
     sämtliche
    2.38
    Activations Density 0.003%

    No Known Activations