Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 46855
    Prev
    Next
    INDEX
    Explanations

    specifying noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tia
    1.15
    ▶
    1.10
    NAMES
    1.08
     spekt
    1.07
    drug
    1.07
     Adası
    1.06
    dict
    1.06
    ty
    1.06
    
    1.06
     தொடர்புடைய
    1.06
    POSITIVE LOGITS
    훤
    1.17
     wohn
    1.09
     welding
    1.07
     lapply
    1.06
     ResponseEntity
    1.03
    ==============]
    1.02
    𝗆
    1.02
     gsap
    1.01
    ೀ
    1.01
     kivy
    1.00
    Activations Density 0.000%

    No Known Activations