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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112947
    Prev
    Next
    INDEX
    Explanations

    sarcoma, melanoma, carcinoma

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

    medical terms related to cancer types, particularly sarcomas and carcinomas.

    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
     nahi
    -1.50
     yake
    -1.43
    躥
    -1.41
     schu
    -1.38
     haer
    -1.38
     abr
    -1.37
     marseille
    -1.36
     carmen
    -1.35
     barnet
    -1.32
     tien
    -1.31
    POSITIVE LOGITS
     of
    1.38
     cuyas
    1.32
    sena
    1.28
     under
    1.26
     like
    1.23
     Christopher
    1.22
     unserer
    1.20
    Ứng
    1.20
    Yw
    1.20
     numerosos
    1.19
    Activations Density 0.501%

    No Known Activations