© 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. 22-GEMMASCOPE-RES-131K
    4. 66742
    Prev
    Next
    INDEX
    Explanations

    other interests and activities

    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
     trattano
    -1.22
    </h2>
    -0.96
    cjonal
    -0.94
    强大
    -0.88
     that
    -0.87
    reamble
    -0.85
    😞
    -0.85
    tigem
    -0.85
    潴
    -0.84
     Pola
    -0.84
    POSITIVE LOGITS
     other
    2.27
    其他
    1.73
     других
    1.64
     autre
    1.61
     otras
    1.58
     outras
    1.55
    อื่น
    1.54
     другие
    1.52
     outros
    1.52
     andere
    1.52
    Activations Density 0.036%

    No Known Activations