© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2110
    Prev
    Next
    INDEX
    Explanations

    full of / filled with

    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_9_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
    紝
    2.89
    it
    2.76
    오늘
    2.70
    বারের
    2.65
    QTTR
    2.62
    裟
    2.57
    ouilles
    2.56
     говоря
    2.56
    polarity
    2.55
    ¿
    2.54
    POSITIVE LOGITS
     coffers
    2.58
     corriente
    2.52
     fled
    2.48
     ocasiones
    2.39
     artich
    2.37
    umination
    2.36
     तरह
    2.34
     تعالى
    2.30
    з
    2.25
     dicas
    2.24
    Activations Density 0.128%

    No Known Activations