© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 87115
    Prev
    Next
    INDEX
    Explanations

    stating, defining, explaining

    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
     They
    -1.81
     also
    -1.63
     schreib
    -1.60
     be
    -1.60
     Their
    -1.56
    upaten
    -1.55
     Also
    -1.42
    或者是
    -1.41
     about
    -1.39
     Whether
    -1.39
    POSITIVE LOGITS
    ſſel
    1.71
    =’
    1.67
    </strong>
    1.41
    唎
    1.35
    =“
    1.33
    :^
    1.29
     wlan
    1.27
    ";}
    1.27
     KEN
    1.27
    fetched
    1.25
    Activations Density 0.213%

    No Known Activations