© 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. 2765
    Prev
    Next
    INDEX
    Explanations

    911 and 988 helplines

    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
     BuildConfig
    0.80
     third
    0.77
     Chimie
    0.71
     nd
    0.70
    ਡ
    0.65
     fourth
    0.65
     결국
    0.65
     calculadora
    0.65
     மூன்ற
    0.64
    oplane
    0.63
    POSITIVE LOGITS
     Deadly
    1.34
    Eleven
    1.28
    th
    1.12
     Eleven
    1.08
     deadly
    1.08
    त्याने
    1.04
     commandments
    1.03
     Habits
    1.00
    Twelve
    1.00
    ⃣
    0.97
    Activations Density 0.423%

    No Known Activations