© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14677
    Prev
    Next
    INDEX
    Explanations

    there anything

    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_31_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
     கூறினார்
    0.58
    வரின்
    0.57
    vier
    0.55
    onial
    0.54
    出来了
    0.54
    рие
    0.54
    私たちの
    0.54
     ର
    0.54
     म्ह
    0.52
    元素的
    0.52
    POSITIVE LOGITS
    ที่คุณ
    1.16
     которую
    1.10
     koju
    1.09
     kterou
    1.06
     whom
    0.93
     التي
    0.90
     яку
    0.88
     którą
    0.86
     Whom
    0.86
    ที่เรา
    0.86
    Activations Density 0.561%

    No Known Activations