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. 9-GEMMASCOPE-2-RES-262K
    4. 7251
    Prev
    Next
    INDEX
    Explanations

    shipping logistics and routes

    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_9_width_262k_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
    ບບ
    1.33
     exponents
    1.30
     そう
    1.21
    istic
    1.18
    굽
    1.17
    इसके
    1.16
     decency
    1.14
     discretion
    1.13
    یت
    1.13
    tained
    1.13
    POSITIVE LOGITS
    e
    1.10
    Reduce
    1.07
     consigo
    1.05
    ㅇ
    1.02
    cua
    1.01
    brains
    1.01
    Cargo
    1.01
    잦
    1.00
    an
    0.98
    会导致
    0.98
    Activations Density 0.147%

    No Known Activations