© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2848
    Prev
    Next
    INDEX
    Explanations

    falso

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     PPR
    0.66
     చె
    0.66
     Shak
    0.65
    accessor
    0.63
    缅
    0.61
     Scratch
    0.61
    亀
    0.61
    菂
    0.61
     سیر
    0.61
    Dana
    0.60
    POSITIVE LOGITS
    olt
    2.20
    ol
    2.10
     ol
    2.00
    OL
    1.96
     Ol
    1.89
    Ol
    1.89
     olt
    1.86
    olta
    1.81
    olf
    1.81
    olm
    1.80
    Activations Density 0.748%

    No Known Activations