© 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. 71692
    Prev
    Next
    INDEX
    Explanations

    that of

    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
    primarily
    -1.29
    mainly
    -1.27
    focused
    -1.23
    の部分
    -1.23
    designed
    -1.23
     gouverneur
    -1.23
    主要是
    -1.21
     také
    -1.21
     mungkin
    -1.20
     péché
    -1.20
    POSITIVE LOGITS
     with
    1.48
     when
    1.43
     only
    1.28
    ahuje
    1.16
    ння
    1.16
     that
    1.16
    }]{
    1.15
    我们要
    1.13
     lho
    1.12
     muualla
    1.11
    Activations Density 0.064%

    No Known Activations