© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65515
    Prev
    Next
    INDEX
    Explanations

    expresses strong negative sentiment

    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
     this
    -1.77
     such
    -1.47
    感じで
    -1.43
    為に
    -1.33
     zwykle
    -1.30
    をしました
    -1.29
    をしていた
    -1.29
     their
    -1.28
    んでしょう
    -1.24
    ようです
    -1.20
    POSITIVE LOGITS
    が
    1.46
     spesifik
    1.44
    と
    1.42
    を
    1.38
    though
    1.35
    5
    1.34
     ESPEC
    1.33
    ate
    1.30
    lio
    1.28
    particularly
    1.28
    Activations Density 0.059%

    No Known Activations