© 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. 109932
    Prev
    Next
    INDEX
    Explanations

    histological inflammation and atrophy

    np_acts-logits-general · gemini-2.5-flash-lite

    medical or histological descriptions of tissue pathology and cellular structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    静静
    -0.94
    ")));
    -0.92
    logr
    -0.88
     cutaneous
    -0.88
     almak
    -0.81
    genous
    -0.79
     estabiliz
    -0.79
     muualla
    -0.77
    yoshi
    -0.76
    ीत
    -0.76
    POSITIVE LOGITS
     congestion
    1.13
     vacu
    0.93
     vac
    0.93
     architectural
    0.92
     architecture
    0.92
     hist
    0.92
     infiltration
    0.89
     inflammation
    0.88
    正常的
    0.86
     architectures
    0.85
    Activations Density 0.265%

    No Known Activations