© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 855
    Prev
    Next
    INDEX
    Explanations

    US states

    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_29_width_16k_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
    อร์ด
    0.64
    stuk
    0.64
     CHIKV
    0.64
    Euler
    0.64
    卓
    0.64
     ముందుకు
    0.64
    TreeNode
    0.61
    ophagy
    0.61
    麟
    0.60
    ListNode
    0.60
    POSITIVE LOGITS
     Pennsylvania
    3.25
     California
    3.14
     Illinois
    3.07
     Florida
    3.02
     Missouri
    3.00
     Texas
    2.99
    Pennsylvania
    2.96
    California
    2.92
     Maryland
    2.90
     Ohio
    2.88
    Activations Density 0.509%

    No Known Activations