© 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. 2550
    Prev
    Next
    INDEX
    Explanations

    multilingual possessives and "I" statements

    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
     baroque
    1.23
     宮
    1.22
    𓏧
    1.21
     mysticism
    1.19
     nirv
    1.17
     svr
    1.16
     vim
    1.15
    squiggle
    1.15
    atória
    1.14
    涧
    1.13
    POSITIVE LOGITS
     aware
    1.41
     capaces
    1.23
     cognizant
    1.12
     capaz
    1.06
    ured
    1.03
     proud
    0.97
     observant
    0.97
     chauffeur
    0.96
     capazes
    0.95
    aware
    0.93
    Activations Density 0.700%

    No Known Activations