© 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. 15045
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

    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
    ier
    0.70
    um
    0.70
    юд
    0.70
    ट
    0.70
    ணி
    0.67
    spunkt
    0.65
    en
    0.65
     "'
    0.65
    ק
    0.64
    ленное
    0.63
    POSITIVE LOGITS
     اخبار
    0.66
     konkurs
    0.61
     iniziamo
    0.60
     pageant
    0.59
     legislação
    0.59
    气息
    0.58
     Debido
    0.57
    开源
    0.57
     ambito
    0.56
     tumultuous
    0.55
    Activations Density 0.089%

    No Known Activations