© 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. 17-GEMMASCOPE-2-RES-16K
    7. 4632
    Prev
    Next
    INDEX
    Explanations

    movie tv film video

    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
    গি
    2.15
    heit
    2.08
    ernetes
    1.99
     ALS
    1.99
    d
    1.98
     abrang
    1.98
    baixo
    1.93
    sembled
    1.90
     cont
    1.89
     разнови
    1.86
    POSITIVE LOGITS
     Каждый
    2.24
     불구하고
    2.16
    >′
    1.99
     televisi
    1.94
     befinden
    1.93
     చూడ
    1.91
     تلویزی
    1.91
    י
    1.91
    ⎛
    1.91
    isión
    1.90
    Activations Density 0.314%

    No Known Activations