© 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. 985
    Prev
    Next
    INDEX
    Explanations

    primary goal or purpose

    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
    Famous
    1.07
    bigger
    1.00
    obviously
    0.97
     sangu
    0.96
    famous
    0.95
    putable
    0.95
     වර්ග
    0.91
    ㄍ
    0.89
    smaller
    0.87
    biggr
    0.87
    POSITIVE LOGITS
     program
    1.38
     coordinator
    1.32
     programs
    1.27
     director
    1.25
     Program
    1.24
     outreach
    1.23
     manager
    1.20
     Programs
    1.19
     department
    1.19
     प्रकोष्ठ
    1.16
    Activations Density 0.477%

    No Known Activations