© 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. 110696
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by common nouns or punctuation

    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
    1
    -3.20
    0
    -3.14
    i
    -2.97
    8
    -2.83
    5
    -2.58
    渽
    -2.56
    6
    -2.47
    9
    -2.45
    3
    -2.41
    4
    -2.41
    POSITIVE LOGITS
    ’
    3.36
    </strong>
    3.00
     
    2.91
    {
    2.84
     There
    2.58
    除此之外
    2.48
     จาก
    2.38
    珽
    2.38
    要不然
    2.28
     We
    2.27
    Activations Density 0.039%

    No Known Activations