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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45532
    Prev
    Next
    INDEX
    Explanations

    echogenic, hypo, tubular, round, cystic

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

    words and phrases used to describe medical imaging findings, particularly terms related to radiographic appearance.

    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
    ΙΣ
    -0.77
    ibat
    -0.77
     uParam
    -0.76
     সে
    -0.75
     Reconciliation
    -0.75
     cramps
    -0.75
    ณี
    -0.75
     yapt
    -0.74
    krankungen
    -0.74
     কর
    -0.72
    POSITIVE LOGITS
     shadows
    1.29
     dark
    1.15
     shadow
    1.14
     enhancement
    1.06
     darkest
    1.04
     density
    0.99
     bright
    0.98
     densities
    0.97
     dense
    0.95
     darkness
    0.93
    Activations Density 0.252%

    No Known Activations