© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67973
    Prev
    Next
    INDEX
    Explanations

    technical resolution

    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
     There
    -2.39
     Like
    -1.95
     Then
    -1.91
     about
    -1.91
     he
    -1.86
     are
    -1.84
    }
    -1.82
     it
    -1.77
     Gibt
    -1.77
    をしました
    -1.76
    POSITIVE LOGITS
    0
    1.95
    for
    1.80
     continuó
    1.78
     :\\
    1.74
    あんまり
    1.67
    搞笑
    1.66
    ियर
    1.65
    但是在
    1.63
    快的
    1.60
     OGSÅ
    1.59
    Activations Density 0.015%

    No Known Activations