© 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. 130224
    Prev
    Next
    INDEX
    Explanations

    recent issue, post-docdum, fire appears, more Jud, salt mouth, conspiracy nuts, graphic arts, low temperatures, portfolio collection

    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
    犼
    -1.84
    ᠁
    -1.84
    螣
    -1.54
    ⭓
    -1.51
     straips
    -1.48
     kteří
    -1.47
    柃
    -1.47
    强制
    -1.46
    ሖ
    -1.45
    ︲
    -1.45
    POSITIVE LOGITS
    0
    2.45
    8
    2.08
     of
    1.95
    5
    1.93
    Each
    1.81
    9
    1.79
    6
    1.76
     each
    1.75
     kebakaran
    1.65
    4
    1.65
    Activations Density 0.937%

    No Known Activations