© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65201
    Prev
    Next
    INDEX
    Explanations

    parent object or container

    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
     about
    -2.19
    x
    -2.02
    or
    -1.98
    k
    -1.92
    and
    -1.88
    z
    -1.63
     необходимые
    -1.48
    s
    -1.47
     they
    -1.45
     become
    -1.43
    POSITIVE LOGITS
    नलोड
    2.13
     rozwią
    1.83
    まさかの
    1.72
     citoy
    1.69
    励志
    1.66
    The
    1.64
     ouvre
    1.63
    Jereo
    1.59
    蒟
    1.57
     resourceful
    1.54
    Activations Density 0.003%

    No Known Activations