© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14607
    Prev
    Next
    INDEX
    Explanations

    scientific questions and statements

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

    sequences of digits, especially when they appear in numeric patterns or identifiers.

    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
     geef
    -1.38
     וכו
    -1.27
     rekke
    -1.24
     strøm
    -1.23
     euró
    -1.23
     olje
    -1.23
     aktivitet
    -1.20
    zdroj
    -1.20
     stratég
    -1.20
     vertelt
    -1.19
    POSITIVE LOGITS
    ata
    1.35
    ia
    1.32
    al
    1.23
    p
    1.20
    chi
    1.20
    l
    1.19
    u
    1.19
    ha
    1.19
    ar
    1.18
    ul
    1.18
    Activations Density 0.000%

    No Known Activations