© 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. 10338
    Prev
    Next
    INDEX
    Explanations

    helpline or support resources

    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
    peliculas
    0.92
     hopelessness
    0.89
     camadas
    0.87
    <unused698>
    0.86
    ляции
    0.86
    FBSDKGraph
    0.86
    snippet
    0.85
     પતિ
    0.84
    texture
    0.83
     bleak
    0.83
    POSITIVE LOGITS
     대해
    1.01
     సంబంధించిన
    0.87
    卉
    0.80
     대하여
    0.77
     Klo
    0.76
     Sensitivity
    0.76
     حساس
    0.76
     대한
    0.73
    ैनल
    0.73
    Overall
    0.72
    Activations Density 0.011%

    No Known Activations