© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13502
    Prev
    Next
    INDEX
    Explanations

    financial costs

    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
    ſtra
    -2.89
    i
    -2.78
    ised
    -2.78
    igrette
    -2.72
    ೞ
    -2.70
    鉝
    -2.63
    鱟
    -2.61
     cappella
    -2.61
    𓐍
    -2.52
    錒
    -2.44
    POSITIVE LOGITS
     overriding
    2.73
     eigene
    2.64
    榈
    2.63
     demandé
    2.44
     tenté
    2.44
     quirks
    2.42
     costs
    2.38
     remplacé
    2.34
    та
    2.31
     ก็
    2.30
    Activations Density 0.005%

    No Known Activations