© 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. 22-GEMMASCOPE-2-RES-262K
    7. 20073
    Prev
    Next
    INDEX
    Explanations

    semantic categories and examples

    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_22_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
    র্শ
    1.07
     நடந்து
    1.05
     interfered
    1.03
     spurred
    1.03
     hampered
    1.02
    𝐬
    1.01
    𝐠
    1.00
    🚅
    0.96
     demanded
    0.96
    𝐢
    0.96
    POSITIVE LOGITS
    в
    1.14
     призна
    0.91
     Igual
    0.82
    dere
    0.81
     individuais
    0.79
    Move
    0.78
    те
    0.75
    ли
    0.74
    вя
    0.74
     ahí
    0.74
    Activations Density 0.000%

    No Known Activations