© 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. 38861
    Prev
    Next
    INDEX
    Explanations

    what was tried

    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
    ⚋
    -1.77
    Ingredienti
    -1.70
     sabias
    -1.48
    Scopri
    -1.48
    婞
    -1.48
    樘
    -1.46
    ClassNotFound
    -1.46
     lâng
    -1.45
     dört
    -1.42
    ]^{-
    -1.41
    POSITIVE LOGITS
     with
    2.80
     including
    1.89
     includes
    1.80
     that
    1.72
     include
    1.55
     in
    1.54
     Includes
    1.53
     like
    1.52
    satu
    1.47
     especially
    1.45
    Activations Density 2.343%

    No Known Activations