© 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. 10405
    Prev
    Next
    INDEX
    Explanations

    ramble or grammatical

    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
    ↪
    0.95
     दुष्
    0.92
    rophys
    0.91
     stirred
    0.91
     Кры
    0.90
     sentimento
    0.90
     digitar
    0.89
     pensée
    0.88
    ‮
    0.88
    xiii
    0.88
    POSITIVE LOGITS
    adhan
    0.98
    irez
    0.97
    matical
    0.90
     APA
    0.85
    यण
    0.83
    აში
    0.82
    ्याल
    0.81
    poline
    0.80
     digamos
    0.78
    atical
    0.77
    Activations Density 0.116%

    No Known Activations