© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20555
    Prev
    Next
    INDEX
    Explanations

    President Donald Trump, President Barack Obama

    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
     görüntüleri
    -1.58
    llac
    -1.56
     a
    -1.38
     kümmern
    -1.34
    </strong>
    -1.32
     widać
    -1.30
     consideró
    -1.27
    šení
    -1.26
    UREAU
    -1.25
    _
    -1.25
    POSITIVE LOGITS
     of
    1.55
    !（
    1.55
    ↵↵
    1.43
     enten
    1.35
    chränkungen
    1.34
    ？？
    1.34
    manın
    1.33
     gratuita
    1.33
    =============
    1.31
    zins
    1.30
    Activations Density 0.036%

    No Known Activations