© 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. 65966
    Prev
    Next
    INDEX
    Explanations

    Introduction scientific or code snippets

    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
    
    -1.59
     this
    -1.38
     هذا
    -1.35
    ಆ
    -1.34
    urator
    -1.33
     هذه
    -1.32
    ڧ
    -1.32
    佉
    -1.31
     tässä
    -1.31
     هنا
    -1.30
    POSITIVE LOGITS
    e
    1.65
    全ての
    1.41
     typical
    1.38
    {\
    1.38
    ”.
    1.34
    8
    1.33
    p
    1.30
     beeinf
    1.27
     proactively
    1.27
    都需要
    1.27
    Activations Density 0.000%

    No Known Activations