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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109813
    Prev
    Next
    INDEX
    Explanations

    celery, parsley, carrot

    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
     rhod
    -0.76
    ims
    -0.75
     teak
    -0.73
     trees
    -0.73
    առ
    -0.71
    不得
    -0.70
    createNew
    -0.70
     Selena
    -0.69
     bông
    -0.69
     projectiles
    -0.68
    POSITIVE LOGITS
     celery
    1.27
    Umb
    1.07
     parsley
    1.04
    celery
    1.01
     carrot
    0.98
     um
    0.98
    セリ
    0.96
     Celery
    0.94
    Ange
    0.93
     Pars
    0.93
    Activations Density 0.051%

    No Known Activations