© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 789
    Prev
    Next
    INDEX
    Explanations

    image or record

    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_17_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
    opcode
    0.87
    Еще
    0.86
    т
    0.86
    Altitude
    0.85
    es
    0.85
    i
    0.84
    Hint
    0.83
    Repeat
    0.83
    Biblioteca
    0.82
    Semaphore
    0.81
    POSITIVE LOGITS
     spearheaded
    0.95
    ുകളാണ്
    0.92
     dejó
    0.85
     direttamente
    0.84
     autonome
    0.83
    ោង
    0.82
     的
    0.82
    ⁧
    0.81
    筫
    0.80
     telah
    0.79
    Activations Density 0.625%

    No Known Activations