© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9150
    Prev
    Next
    INDEX
    Explanations

    complete tasks or requests

    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
    توان
    2.97
    :'',
    2.85
    aş
    2.74
    aży
    2.68
    a
    2.50
    wards
    2.49
    𝗴
    2.47
    𝗸
    2.47
    eos
    2.46
    ה
    2.45
    POSITIVE LOGITS
     حجت
    3.01
    fledged
    2.48
    माँ
    2.44
    ளாக்
    2.42
    ist
    2.33
    erton
    2.28
     dentures
    2.25
    ید
    2.25
    Situated
    2.24
     века
    2.24
    Activations Density 0.055%

    No Known Activations