© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74571
    Prev
    Next
    INDEX
    Explanations

    open university, hazel grace, Jane Velez-Mitchell, Wellness Tip, fashion style, Blackpool UK, Dani Hernández

    np_acts-logits-general · gemini-2.5-flash-lite

    Python, ChatGPT, mobile, food, Office, Nature, Year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ोल
    0.41
    嘜
    0.38
    網友
    0.36
    歟
    0.36
    是从
    0.36
     নো
    0.36
     COMPENSATION
    0.35
     exploratory
    0.35
    ၊
    0.34
    BEST
    0.34
    POSITIVE LOGITS
     বালক
    0.41
    ційний
    0.41
    ermost
    0.38
    either
    0.37
     nacido
    0.37
    とめ
    0.37
    BuildConfig
    0.37
    )‏
    0.35
    ിയാണ്
    0.35
    ುದು
    0.35
    Activations Density 0.011%

    No Known Activations