© 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. 22-GEMMASCOPE-RES-131K
    7. 95571
    Prev
    Next
    INDEX
    Explanations

    proper nouns and acronyms

    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
     geloof
    -1.27
    ፝
    -1.27
     raccont
    -1.25
    ⤞
    -1.23
    のご紹介
    -1.23
     interessant
    -1.22
    マジで
    -1.21
    føring
    -1.20
    औ
    -1.20
    Perú
    -1.20
    POSITIVE LOGITS
     actually
    1.29
     versions
    1.20
     sämtliche
    1.17
    to
    1.13
    '
    1.12
     mechanisms
    1.10
    !!!!!!
    1.10
    r
    1.08
    而不
    1.07
    而非
    1.07
    Activations Density 0.041%

    No Known Activations