© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 926
    Prev
    Next
    INDEX
    Explanations

    science suffix -ology analysis

    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_16k_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
     made
    1.45
     Cop
    1.33
     for
    1.32
     O
    1.27
     Com
    1.25
     US
    1.25
    ↵↵
    1.24
     to
    1.24
     o
    1.23
     sold
    1.22
    POSITIVE LOGITS
    ologische
    2.84
    acją
    2.71
    ometrical
    2.66
    ographical
    2.65
    ologisk
    2.64
    ographic
    2.63
    ogical
    2.63
    ologically
    2.63
    otechnical
    2.59
    ologischen
    2.58
    Activations Density 0.959%

    No Known Activations