© 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-262K
    7. 149788
    Prev
    Next
    INDEX
    Explanations

    ordered pairs

    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
     Boolean
    0.60
    罫
    0.60
     missp
    0.60
    ้าง
    0.59
     प्रतिनिध
    0.59
    ப்பட
    0.58
    াব্দ
    0.58
     incorrect
    0.58
    ivational
    0.57
    فته
    0.57
    POSITIVE LOGITS
    Cry
    0.82
     Cry
    0.77
    Eco
    0.76
    Brain
    0.76
    넓
    0.74
     Brain
    0.74
     Tri
    0.74
    Influence
    0.73
    azaar
    0.73
    Ster
    0.72
    Activations Density 0.001%

    No Known Activations