© 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. 103604
    Prev
    Next
    INDEX
    Explanations

    questions starting with Q or specific names

    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
     all
    -1.44
     shady
    -1.36
     OGSÅ
    -1.34
     \%$.
    -1.33
    すべての
    -1.30
    荽
    -1.29
    able
    -1.26
    菔
    -1.25
     hochwer
    -1.25
     ebb
    -1.23
    POSITIVE LOGITS
     fuir
    1.59
    🫓
    1.47
     almeno
    1.45
     réessayer
    1.42
     Visited
    1.41
     normais
    1.41
     内衣
    1.40
    踭
    1.39
     diriger
    1.39
     Directly
    1.38
    Activations Density 0.009%

    No Known Activations