© 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. 15310
    Prev
    Next
    INDEX
    Explanations

    contrary conjunctions

    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
    砜
    -0.84
    rcl
    -0.79
     aident
    -0.79
    ificador
    -0.79
    ceiro
    -0.78
    стреча
    -0.78
    anias
    -0.77
    scaler
    -0.76
    Willkommen
    -0.74
    𝖽
    -0.74
    POSITIVE LOGITS
     that
    1.03
     trotzdem
    1.00
     because
    0.87
    Nevertheless
    0.85
     still
    0.82
    Dav
    0.82
     dennoch
    0.81
     Nevertheless
    0.81
     nevertheless
    0.81
    这个
    0.80
    Activations Density 0.030%

    No Known Activations