© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3104
    Prev
    Next
    INDEX
    Explanations

    word pairs connected by and or

    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
     và
    0.53
    −
    0.43
    와
    0.42
     quale
    0.42
    或其他
    0.42
     ă
    0.41
     beinh
    0.41
    -'
    0.41
     swivel
    0.41
     supremo
    0.40
    POSITIVE LOGITS
    धियों
    0.51
    including
    0.49
     воспомина
    0.48
     घटनाओं
    0.47
     включая
    0.47
     idiomas
    0.46
    cultures
    0.46
     исторических
    0.45
    ेशंस
    0.45
     учреждений
    0.44
    Activations Density 0.510%

    No Known Activations