© 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-16K
    7. 10346
    Prev
    Next
    INDEX
    Explanations

    tal, tel, tell, tall

    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_16k_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
    ਉਣ
    0.92
    ក៏
    0.86
    fighting
    0.78
    公式サイト
    0.77
    aktual
    0.77
    uacao
    0.77
    垢
    0.76
    fight
    0.75
     يكون
    0.75
    यला
    0.75
    POSITIVE LOGITS
    rijke
    0.86
     tal
    0.86
    ega
    0.83
     નિ
    0.81
    íř
    0.81
    کین
    0.80
     волос
    0.78
    uride
    0.78
     Tale
    0.77
    ቅ
    0.76
    Activations Density 0.088%

    No Known Activations