Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12134
    Prev
    Next
    INDEX
    Explanations

    contrastive 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
     and
    -1.69
     will
    -1.09
     N
    -1.09
     before
    -1.07
    0
    -1.06
    ərbaycan
    -1.06
    1
    -1.05
    7
    -1.05
    your
    -1.04
    wijze
    -1.04
    POSITIVE LOGITS
    Conclusión
    1.56
     toutefois
    1.48
     Então
    1.45
     that
    1.34
     Também
    1.34
     Entonces
    1.33
    twas
    1.29
     hés
    1.27
    觧
    1.25
     então
    1.24
    Activations Density 0.016%

    No Known Activations