© 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. 9481
    Prev
    Next
    INDEX
    Explanations

    logging statements

    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
    𝑜
    3.13
     akhirnya
    3.09
    𝐞
    2.96
     asunto
    2.77
     રીતે
    2.76
     uncont
    2.67
    itore
    2.65
     hende
    2.63
     posibil
    2.62
     đủ
    2.61
    POSITIVE LOGITS
    ي
    2.81
    öm
    2.63
    ভেদ
    2.63
    बाजी
    2.58
    муж
    2.52
    л
    2.51
    犸
    2.49
    ed
    2.49
    oğlu
    2.48
    രള
    2.47
    Activations Density 0.013%

    No Known Activations