© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 213
    Prev
    Next
    INDEX
    Explanations

    code and mathematical formulas

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

    the presence of numeric literals (numbers) in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     for
    -1.28
    A
    -1.27
     we
    -1.16
    D
    -1.16
    V
    -1.15
    P
    -1.14
     this
    -1.14
     our
    -1.10
    De
    -1.10
    for
    -1.09
    POSITIVE LOGITS
     patatas
    1.09
    daki
    1.09
    Zé
    1.08
    Efe
    1.07
     parques
    1.04
     Mavericks
    1.03
     reaksi
    1.03
    mdan
    1.03
     Slayer
    1.02
     expérience
    1.02
    Activations Density 0.007%

    No Known Activations