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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22163
    Prev
    Next
    INDEX
    Explanations

    Titanfall, Titan pickup, Titanate

    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
    凊
    -2.95
     цього
    -2.80
    閙
    -2.73
    ῞
    -2.72
    人是
    -2.70
    ción
    -2.70
    扨
    -2.56
    
    -2.56
    ⑊
    -2.55
     eigenes
    -2.47
    POSITIVE LOGITS
    {
    3.23
    </h1>
    3.19
    </i>
    2.98
     be
    2.66
     вопрос
    2.58
    )」
    2.48
     необходимо
    2.44
    もや
    2.28
    がんば
    2.27
     It
    2.25
    Activations Density 0.003%

    No Known Activations