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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9912
    Prev
    Next
    INDEX
    Explanations

    hunger

    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
    م
    3.29
    ⃣
    3.25
    त
    3.10
    ️⃣
    3.01
    speople
    2.94
     बचने
    2.87
    ット
    2.78
     மூலம்
    2.66
    完毕
    2.63
    cador
    2.60
    POSITIVE LOGITS
    ة
    2.81
     hê
    2.36
     acre
    2.30
    us
    2.30
    ло
    2.28
    Household
    2.28
    S
    2.27
    oré
    2.22
    क्यूमेंट
    2.22
     Aufgabe
    2.22
    Activations Density 0.044%

    No Known Activations