© 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. 936
    Prev
    Next
    INDEX
    Explanations

    cranial anatomy and medical imaging

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

    terms related to cranial anatomy and medical conditions affecting the skull and nerves.

    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
    袮
    -2.31
    We
    -2.30
    when
    -2.28
    ꜆
    -2.28
    ाइल
    -2.16
     palazzo
    -2.14
    铪
    -2.14
     lopez
    -2.06
     fazia
    -2.02
    '
    -2.00
    POSITIVE LOGITS
     einfache
    2.39
    ’
    2.30
    を増
    2.22
     развития
    2.19
    哂
    2.16
     небольшой
    2.14
     elaborate
    2.13
     respective
    2.11
    AdvEx
    2.06
    _{
    2.02
    Activations Density 0.014%

    No Known Activations