© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 920
    Prev
    Next
    INDEX
    Explanations

    Albania

    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
    ining
    0.45
    숀
    0.45
    '")
    0.44
    aran
    0.43
    कित
    0.42
    onne
    0.41
     පැ
    0.41
    itespace
    0.41
    帷
    0.40
    ାର
    0.40
    POSITIVE LOGITS
    𝘳
    0.53
     natürlichen
    0.49
     an
    0.47
    姣
    0.47
     arbres
    0.47
     contenuto
    0.47
     essa
    0.46
     décrite
    0.46
     árv
    0.46
     öffentlichen
    0.46
    Activations Density 0.002%

    No Known Activations