© 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. 68953
    Prev
    Next
    INDEX
    Explanations

    business services hours

    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
    dirond
    -1.34
     avião
    -1.18
     episódio
    -1.14
    StandardCharsets
    -1.14
    asil
    -1.13
    🩹
    -1.13
     caufe
    -1.12
     passeio
    -1.10
    satunya
    -1.09
     efeito
    -1.07
    POSITIVE LOGITS
     business
    1.13
     not
    1.09
     européennes
    1.05
     services
    1.04
     POS
    1.01
     if
    1.00
    ーと
    1.00
     so
    0.99
    丕
    0.98
     as
    0.98
    Activations Density 0.002%

    No Known Activations