© 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. 4500
    Prev
    Next
    INDEX
    Explanations

    significant differences

    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
    し
    0.61
    ors
    0.59
    species
    0.59
    지만
    0.55
     கொஞ்சம்
    0.54
     Ах
    0.54
     Surgeons
    0.53
    simple
    0.53
    ę
    0.53
     Бу
    0.52
    POSITIVE LOGITS
    (
    0.77
    .
    0.68
     financi
    0.66
     verschil
    0.66
     تغيير
    0.65
     changement
    0.64
    ва
    0.60
     Unterschied
    0.60
     différence
    0.59
     (>
    0.58
    Activations Density 0.238%

    No Known Activations