© 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-262K
    7. 12054
    Prev
    Next
    INDEX
    Explanations

    mysterious ability from process

    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
    introspection
    1.46
    𝗱
    1.19
     विरा
    1.19
     бата
    1.18
    )],
    1.15
     институт
    1.13
    內的
    1.12
    innerApiCalls
    1.12
    progressBar
    1.10
    ྞ
    1.10
    POSITIVE LOGITS
    лих
    1.46
     profit
    1.40
    er
    1.35
    ہ
    1.34
    সংখ্যক
    1.33
    nement
    1.30
     friendly
    1.29
     excuse
    1.29
     dozen
    1.29
    ব্যাপী
    1.28
    Activations Density 0.000%

    No Known Activations