© 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. 75111
    Prev
    Next
    INDEX
    Explanations

    professional music careers and deals

    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
    ଷ
    -1.17
     use
    -1.13
    '&:
    -1.09
     RSSSF
    -1.05
     книги
    -1.05
    գ
    -1.02
    ༄
    -1.02
    }{%
    -1.02
    ğimiz
    -1.00
    brin
    -1.00
    POSITIVE LOGITS
    ؔ
    1.44
    チュア
    1.29
     professionalism
    1.22
     unsigned
    1.20
     musíte
    1.16
    elance
    1.13
     career
    1.13
     authentique
    1.11
    asants
    1.11
    flich
    1.08
    Activations Density 0.050%

    No Known Activations