© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8173
    Prev
    Next
    INDEX
    Explanations

    jointly, mutually, exchange

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    iennent
    0.41
    ailleurs
    0.40
    𝓈
    0.39
     relações
    0.39
     separa
    0.38
    サスカ
    0.37
    वर्गीय
    0.37
    𝒃
    0.37
    燧
    0.36
    愛的
    0.36
    POSITIVE LOGITS
     jointly
    0.47
     ampliar
    0.47
     mutually
    0.47
     exchange
    0.45
     ortak
    0.44
     공동
    0.44
     joint
    0.44
     triangulation
    0.43
    共同
    0.42
    扩大
    0.42
    Activations Density 0.251%

    No Known Activations