© 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. 64914
    Prev
    Next
    INDEX
    Explanations

    contrary or opposite

    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
    følge
    -0.90
     brush
    -0.87
    izmus
    -0.85
    cauciones
    -0.85
     view
    -0.82
     Strategie
    -0.82
    MessageDigest
    -0.82
    اض
    -0.81
     ner
    -0.80
    ativos
    -0.80
    POSITIVE LOGITS
     Conversely
    1.78
    Conversely
    1.73
     conversely
    1.70
     наоборот
    1.30
    逆に
    1.13
     umgekehrt
    1.09
     sebaliknya
    1.09
    相反
    1.02
     viceversa
    1.02
     opposite
    1.00
    Activations Density 0.180%

    No Known Activations