© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9070
    Prev
    Next
    INDEX
    Explanations

    years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    부터
    0.67
     এইভাবে
    0.65
     якобы
    0.62
    에
    0.61
    нические
    0.58
     সমস্ত
    0.57
     뭔가
    0.56
    점에
    0.56
     vowel
    0.55
     সাধারণভাবে
    0.55
    POSITIVE LOGITS
    و
    0.74
    girlfriend
    0.59
    𝐬
    0.57
    entimes
    0.55
    𝘀
    0.54
    operatorname
    0.53
    r
    0.53
    ‍♀️
    0.51
    ik
    0.51
    斯特
    0.49
    Activations Density 0.031%

    No Known Activations