© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1385
    Prev
    Next
    INDEX
    Explanations

    words starting with articles

    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_34/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
     others
    -1.20
     ótima
    -1.05
    ifiers
    -1.05
    裥
    -0.98
     other
    -0.96
    }*/
    -0.94
     ocasião
    -0.91
    inerario
    -0.90
     coroa
    -0.90
    したのが
    -0.90
    POSITIVE LOGITS
     woman
    1.73
     employee
    1.30
     group
    1.28
     former
    1.27
     young
    1.24
     British
    1.24
     retired
    1.24
     student
    1.20
     married
    1.20
     Nigerian
    1.18
    Activations Density 0.153%

    No Known Activations