© 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. 897
    Prev
    Next
    INDEX
    Explanations

    medical tumors and functions

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

    medical and scientific text related to diseases, particularly tumors and cancer.

    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
    journalist
    -1.35
    gume
    -1.31
     ständig
    -1.30
    aried
    -1.27
    nachron
    -1.23
    Ἀ
    -1.22
    wochen
    -1.22
    ruary
    -1.20
     amenazas
    -1.20
    selben
    -1.17
    POSITIVE LOGITS
     their
    1.36
     think
    1.27
     see
    1.27
     getting
    1.23
     with
    1.22
     will
    1.21
     there
    1.19
    겠
    1.15
     that
    1.15
     помогут
    1.14
    Activations Density 1.543%

    No Known Activations