© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10072
    Prev
    Next
    INDEX
    Explanations

    words followed by common endings

    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_262k_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
    ة
    3.05
    াহিয়া
    2.63
    း
    2.55
     richly
    2.54
    ?!?
    2.50
    ]));
    2.48
    ActionBar
    2.47
    visory
    2.44
     Nxg
    2.41
    کنندگان
    2.32
    POSITIVE LOGITS
    s
    4.07
    р
    3.86
    ｬ
    3.66
    ت
    3.49
    ר
    3.39
    ের
    3.26
    র
    3.05
    িং
    2.97
    midt
    2.94
    y
    2.94
    Activations Density 0.187%

    No Known Activations