© 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. 70159
    Prev
    Next
    INDEX
    Explanations

    code execution commands

    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
    logía
    -1.30
     primeira
    -1.23
     thier
    -1.19
     stylish
    -1.18
     before
    -1.16
    太大
    -1.15
     benih
    -1.14
    ığınız
    -1.13
     getEmail
    -1.13
    izó
    -1.13
    POSITIVE LOGITS
    ,
    1.48
     Its
    1.39
     it
    1.38
    它
    1.31
    男の子
    1.23
     Ayrıca
    1.23
     Gegensatz
    1.20
     incendie
    1.16
    ]-\
    1.15
     annak
    1.14
    Activations Density 0.102%

    No Known Activations