© 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
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 17406
    Prev
    Next
    INDEX
    Explanations

    jointly or pair existence

    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_24_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
    Produced
    0.64
    poco
    0.63
    Concent
    0.62
    Corps
    0.61
    8
    0.61
    ING
    0.61
    牍
    0.61
    notch
    0.59
     PRODU
    0.58
    9
    0.58
    POSITIVE LOGITS
    夫妻
    0.70
     dual
    0.66
     jointly
    0.66
     ஆகியோர்
    0.65
     juntos
    0.63
     совме
    0.63
     joint
    0.63
    timevals
    0.62
    倆
    0.62
    respectively
    0.61
    Activations Density 0.003%

    No Known Activations