© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10493
    Prev
    Next
    INDEX
    Explanations

    don't get

    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
    縦
    1.00
     hybr
    0.96
     vertebr
    0.94
     proyect
    0.93
     largeur
    0.92
     extensión
    0.92
     híbr
    0.91
    ፆ
    0.90
     length
    0.89
     Fiberglass
    0.89
    POSITIVE LOGITS
     Homework
    1.27
    homework
    1.24
    Homework
    1.22
     homework
    1.21
     buy
    1.08
    buy
    1.07
     Cheapest
    1.04
    cheap
    1.02
    assignment
    0.99
     cheapest
    0.98
    Activations Density 0.200%

    No Known Activations