© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 2166
    Prev
    Next
    INDEX
    Explanations

    current state of affairs

    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
    er
    4.53
    ার
    3.51
    h
    2.97
    ER
    2.85
    ी
    2.68
    い
    2.52
    ্স
    2.51
    탓
    2.39
    huge
    2.38
    groupBox
    2.36
    POSITIVE LOGITS
    taker
    2.97
     affairs
    2.77
     predicament
    2.75
    Coroutine
    2.71
     vogue
    2.60
     eram
    2.58
     anarchy
    2.58
     hongos
    2.58
     inflict
    2.58
     axle
    2.58
    Activations Density 0.189%

    No Known Activations