© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12774
    Prev
    Next
    INDEX
    Explanations

    storyteller and point of view

    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_22/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
     indicó
    -1.31
     policies
    -1.20
     staff
    -1.17
    紮
    -1.14
     erity
    -1.12
    </em>
    -1.11
     |
    -1.09
    ."
    -1.06
     destacó
    -1.05
     thereunder
    -1.04
    POSITIVE LOGITS
     narrator
    1.45
     algodón
    1.37
     narration
    1.28
    usions
    1.24
    tedly
    1.23
    iress
    1.23
    ༵
    1.23
     Sejarah
    1.22
     mentales
    1.22
     ὑ
    1.21
    Activations Density 0.037%

    No Known Activations