© 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. 85716
    Prev
    Next
    INDEX
    Explanations

    human rights

    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
     regeringen
    -1.38
    itinéraire
    -1.32
     regering
    -1.30
     повітря
    -1.30
    Người
    -1.29
     erwähnten
    -1.27
     міся
    -1.26
     preocupaciones
    -1.24
     със
    -1.23
    erdings
    -1.22
    POSITIVE LOGITS
     they
    1.71
    their
    1.38
     you
    1.36
    俨
    1.34
    Their
    1.22
     Their
    1.20
     leur
    1.19
     tiveram
    1.18
    they
    1.16
     picante
    1.16
    Activations Density 0.103%

    No Known Activations