© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 239
    Prev
    Next
    INDEX
    Explanations

    that followed by a verb

    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_22_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
     and
    1.13
    及其
    1.13
    และ
    1.12
     आणि
    1.11
     والم
    1.11
    and
    1.10
    และการ
    1.09
     и
    1.05
     và
    1.05
    Here
    1.02
    POSITIVE LOGITS
     nobody
    1.72
     many
    1.49
     everyone
    1.49
    大家都
    1.44
     everybody
    1.44
    nobody
    1.42
     pertains
    1.39
     anyone
    1.38
     pertain
    1.35
    许多
    1.34
    Activations Density 1.350%

    No Known Activations