© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9457
    Prev
    Next
    INDEX
    Explanations

    naked or bare with subsequent noun

    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
    𝙣
    3.09
    та
    2.91
     αργ
    2.91
    魎
    2.89
    的安全
    2.77
    ял
    2.69
    𝙜
    2.66
    𝘼
    2.66
    的首
    2.65
    ঁ
    2.61
    POSITIVE LOGITS
    ل
    6.10
    ر
    5.57
    ר
    5.52
    er
    5.01
    र
    4.49
    el
    4.36
    ために
    4.30
    ان
    3.93
    ל
    3.83
    ות
    3.81
    Activations Density 0.056%

    No Known Activations