© 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. 7661
    Prev
    Next
    INDEX
    Explanations

    ramp, ramped up, integral polytope, combinations

    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
     But
    -2.77
     That
    -2.73
     Again
    -2.64
     wiederhol
    -2.53
     consiguió
    -2.52
     However
    -2.50
     Gegensatz
    -2.47
     Gedanke
    -2.41
     Could
    -2.34
    أت
    -2.34
    POSITIVE LOGITS
    虓
    3.03
    ༷
    2.81
    ቺ
    2.58
    ⬮
    2.42
    itizing
    2.41
    躏
    2.39
    鱨
    2.39
    t
    2.34
     защиту
    2.34
    p
    2.28
    Activations Density 0.001%

    No Known Activations