© 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. 54215
    Prev
    Next
    INDEX
    Explanations

    molecular subtypes and signatures

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

    text describing molecular subtypes of cancer or disease classifications.

    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
    ワイイ
    -0.77
     raconter
    -0.77
    चित
    -0.75
     Protocols
    -0.75
    punkte
    -0.75
    jata
    -0.74
     Sociological
    -0.74
    adjustable
    -0.73
     compleanno
    -0.72
     Mandatory
    -0.72
    POSITIVE LOGITS
     signature
    1.32
     signatures
    1.31
     subtype
    1.21
     subtypes
    1.12
     molecular
    1.11
    Subtype
    1.11
    Signature
    1.10
    signature
    1.07
     Signature
    1.06
    Molecular
    0.99
    Activations Density 0.092%

    No Known Activations