© 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. 84035
    Prev
    Next
    INDEX
    Explanations

    available versions and sizes

    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
     first
    -1.68
    וּ
    -1.54
     that
    -1.28
    וֹ
    -1.28
     essential
    -1.26
     favorece
    -1.25
    ִּ
    -1.23
    它的
    -1.22
     nearing
    -1.22
     improving
    -1.17
    POSITIVE LOGITS
     senza
    1.55
     abſ
    1.45
    zonder
    1.41
     également
    1.37
    𓆏
    1.34
     prefeitura
    1.33
    стин
    1.32
     ſur
    1.25
     deine
    1.23
    Makes
    1.22
    Activations Density 0.065%

    No Known Activations