© 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-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 394
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    languageTag
    1.68
     rebuke
    1.65
     relentless
    1.61
     causative
    1.59
    showAlert
    1.57
    कतों
    1.56
    伎
    1.56
     unrelenting
    1.55
    기와
    1.52
    兎
    1.51
    POSITIVE LOGITS
    tok
    1.32
     Sele
    1.31
    ilangkan
    1.30
    alus
    1.27
    wal
    1.27
     Design
    1.25
    sen
    1.25
    n
    1.24
    kon
    1.24
     جان
    1.23
    Activations Density 0.000%

    No Known Activations