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. 29-GEMMASCOPE-2-RES-262K
    4. 283
    Prev
    Next
    INDEX
    Explanations

    red compounds and 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_29_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
     revenus
    0.70
     estim
    0.68
    arly
    0.68
     SDG
    0.67
    DRO
    0.63
     Bhan
    0.63
     abbreviated
    0.63
    午
    0.62
     Equally
    0.62
     tugas
    0.62
    POSITIVE LOGITS
    oubt
    1.57
    dish
    1.52
    emptive
    1.52
    undant
    1.46
    色的
    1.39
    emption
    1.35
     haired
    1.24
    색
    1.24
     رنگ
    1.21
    haired
    1.20
    Activations Density 0.117%

    No Known Activations