© 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. 72887
    Prev
    Next
    INDEX
    Explanations

    negative or restrictive phrases

    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
     of
    -1.82
     in
    -1.26
     more
    -1.23
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.12
    ㄕ
    -1.10
     foran
    -1.09
     uses
    -1.09
     further
    -1.08
    的其他
    -1.03
     extraordinaire
    -0.98
    POSITIVE LOGITS
     insbesondere
    1.29
     Orrell
    1.27
     głównie
    1.21
     generaciones
    1.19
     edades
    1.18
     including
    1.17
     szczególnie
    1.16
    colta
    1.13
     najczęściej
    1.12
     pojawia
    1.11
    Activations Density 0.146%

    No Known Activations