© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127509
    Prev
    Next
    INDEX
    Explanations

    modern storage

    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
    Negative Logits
    趼
    -2.70
     These
    -2.67
    They
    -2.61
    旆
    -2.61
    It
    -2.58
    縺
    -2.58
    ￬
    -2.55
    儇
    -2.52
     intitulée
    -2.48
     meditación
    -2.45
    POSITIVE LOGITS
    ”
    3.20
    O
    2.97
    r
    2.92
    {
    2.92
     \
    2.89
    M
    2.77
    T
    2.67
    U
    2.64
    n
    2.53
    ]
    2.48
    Activations Density 0.001%

    No Known Activations