© 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. 4291
    Prev
    Next
    INDEX
    Explanations

    the followed by English nouns

    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
     ह
    0.44
     mind
    0.44
     немає
    0.42
     dearth
    0.39
     world
    0.39
     cies
    0.39
     monde
    0.37
    actifs
    0.37
     spree
    0.37
    ｈ
    0.36
    POSITIVE LOGITS
     একটি
    0.49
     একই
    0.48
     dezelfde
    0.47
    的一个
    0.47
    }),
    0.44
    selfobj
    0.44
    创建一个
    0.42
     einer
    0.41
    的一些
    0.41
    a
    0.41
    Activations Density 0.157%

    No Known Activations