© 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. 2330
    Prev
    Next
    INDEX
    Explanations

    unusual and strange

    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
     Villanova
    0.51
    汎
    0.47
     Phon
    0.47
     grasslands
    0.45
     Appellate
    0.44
    、
    0.44
     Salaam
    0.44
    i
    0.44
    सू
    0.43
    ，
    0.43
    POSITIVE LOGITS
     weird
    1.04
    奇怪
    1.04
     strange
    0.96
     bizarre
    0.95
    weird
    0.89
     étr
    0.84
    Strange
    0.84
     Weird
    0.84
     অদ্ভুত
    0.82
     unusual
    0.81
    Activations Density 0.430%

    No Known Activations