© 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. 1066
    Prev
    Next
    INDEX
    Explanations

    advice and guidance

    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
    :
    -1.63
     administrativa
    -1.56
     You
    -1.50
     An
    -1.48
     E
    -1.47
    だよ
    -1.46
    ...
    -1.45
     Rather
    -1.43
     That
    -1.41
     А
    -1.41
    POSITIVE LOGITS
     and
    2.73
     بشأن
    1.69
     nových
    1.65
    bauen
    1.63
     zwarte
    1.59
     للبيع
    1.59
    選んだ
    1.57
     egens
    1.56
     początku
    1.55
     dalších
    1.55
    Activations Density 0.043%

    No Known Activations