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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11390
    Prev
    Next
    INDEX
    Explanations

    study, investigation, patients

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

    locations or places in academic papers, particularly when they appear after commas, such as cities, countries, or institutions.

    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_22/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
    𐀀
    -1.35
    zegovina
    -1.33
    rosserie
    -1.22
    盉
    -1.20
     hyvin
    -1.17
     և
    -1.16
    DrawerLayout
    -1.16
    \;
    -1.15
     которого
    -1.14
     JMenuItem
    -1.14
    POSITIVE LOGITS
     Ayam
    1.20
     thereby
    1.05
     students
    1.05
    辺
    1.04
     Moderato
    1.02
    Ti
    1.01
    //<
    1.00
    VENUE
    1.00
     use
    0.98
     parseFloat
    0.98
    Activations Density 0.010%

    No Known Activations