© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2469
    Prev
    Next
    INDEX
    Explanations

    days followed by closing quote punctuation

    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_22_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
    蓦
    0.61
    लिब्र
    0.60
     “
    0.60
     træ
    0.59
    ugging
    0.58
    +:
    0.58
    ächer
    0.58
    ↵
    0.57
     কাছ
    0.57
    నో
    0.57
    POSITIVE LOGITS
    .")
    3.16
    。」
    3.15
    ."
    3.13
    。”
    3.05
    .”
    3.05
    .”)
    3.00
    ."]
    2.96
    .",
    2.80
    ?"
    2.75
    !"
    2.71
    Activations Density 1.329%

    No Known Activations