© 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. 34-GEMMASCOPE-RES-131K
    7. 108181
    Prev
    Next
    INDEX
    Explanations

    numbers and decimal points

    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_34/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
    "../
    -1.32
     ioe
    -1.25
    ♀
    -1.24
    $
    -1.23
     {}));
    -1.22
     gese
    -1.21
    ₙ
    -1.21
     januari
    -1.21
     correctes
    -1.21
    "%(
    -1.20
    POSITIVE LOGITS
     flera
    1.50
     verschiedenen
    1.40
     zahlreichen
    1.30
     mehreren
    1.25
     folgender
    1.23
     terceira
    1.19
    B
    1.18
    u
    1.15
     prachtige
    1.15
     anschließend
    1.15
    Activations Density 0.047%

    No Known Activations