© 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. 10112
    Prev
    Next
    INDEX
    Explanations

    first number in a sequence

    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
     italien
    -1.63
     panor
    -1.59
     amerikan
    -1.59
     minder
    -1.55
     journaliste
    -1.52
     zwei
    -1.52
    ⟣
    -1.52
     certaines
    -1.51
     peintre
    -1.50
     directeur
    -1.48
    POSITIVE LOGITS
     of
    2.45
     instantly
    1.54
    5
    1.53
    4
    1.48
     like
    1.47
     in
    1.43
    此前
    1.42
    of
    1.42
    的在
    1.41
    roughts
    1.39
    Activations Density 0.032%

    No Known Activations