© 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. 923
    Prev
    Next
    INDEX
    Explanations

    accident or chance

    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
    菹
    -1.88
    ncy
    -1.65
    ཥ
    -1.59
     yalnızca
    -1.59
    ⩕
    -1.53
    ꙰
    -1.52
    reasonable
    -1.52
    ⁛
    -1.52
    ntable
    -1.50
    xnn
    -1.50
    POSITIVE LOGITS
     that
    2.45
    2
    2.41
    3
    2.17
    c
    1.91
    4
    1.83
    1
    1.81
    m
    1.81
     when
    1.79
    x
    1.72
    t
    1.70
    Activations Density 0.011%

    No Known Activations