© 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. 10-GEMMASCOPE-RES-131K
    7. 119911
    Prev
    Next
    INDEX
    Explanations

    squamous cell carcinoma

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

    terminology and proper nouns within specialized or technical fields.

    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_10/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
    BeforeClass
    -1.50
    ",
    -1.41
    ongs
    -1.38
     déroule
    -1.38
     we
    -1.38
    で
    -1.34
     etiam
    -1.34
     addition
    -1.25
    we
    -1.24
    нец
    -1.23
    POSITIVE LOGITS
     like
    1.40
    .
    1.26
     Habitats
    1.21
    Hvem
    1.21
    Ilustra
    1.21
    같
    1.20
     نداشت
    1.20
     but
    1.20
    Papier
    1.20
    Bety
    1.18
    Activations Density 0.095%

    No Known Activations