© 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. 47586
    Prev
    Next
    INDEX
    Explanations

    email headers and dates

    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
    водом
    -1.59
    着一
    -1.59
     теми
    -1.46
     möjligt
    -1.45
     "",
    -1.38
     ("
    -1.38
     "
    -1.32
    ("
    -1.27
     ворота
    -1.25
     ähnliche
    -1.24
    POSITIVE LOGITS
     their
    1.84
     they
    1.37
     now
    1.32
     either
    1.30
     when
    1.23
     wesentlichen
    1.17
    OREM
    1.17
    言った
    1.16
    inigung
    1.15
     him
    1.14
    Activations Density 0.004%

    No Known Activations