© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14117
    Prev
    Next
    INDEX
    Explanations

    internal monologue, external influences

    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_7_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
     확실
    1.65
    早く
    1.56
    先の
    1.51
    あった
    1.48
     વધુ
    1.47
     segera
    1.43
    ielten
    1.43
     좀
    1.41
    稍
    1.41
    かなり
    1.41
    POSITIVE LOGITS
     gamut
    1.61
     labyr
    1.42
     spectrum
    1.22
     entera
    1.19
     labyrinth
    1.14
     hela
    1.13
     gama
    1.12
     condem
    1.11
     maze
    1.11
     encapsulates
    1.10
    Activations Density 0.294%

    No Known Activations