© 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. 22-GEMMASCOPE-RES-131K
    7. 104342
    Prev
    Next
    INDEX
    Explanations

    AP news and site search

    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_22/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
    illets
    -0.91
    barred
    -0.87
    pecabe
    -0.86
    itif
    -0.85
    <0x9D>
    -0.84
    Parties
    -0.82
     Германии
    -0.81
     montré
    -0.81
    AFFIRMED
    -0.81
     ſon
    -0.81
    POSITIVE LOGITS
     designated
    0.79
     achieving
    0.77
     Along
    0.77
    Venti
    0.76
     now
    0.76
     him
    0.75
    čku
    0.74
    kait
    0.74
    &
    0.73
    𝘶
    0.73
    Activations Density 0.003%

    No Known Activations