© 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-65K
    7. 3317
    Prev
    Next
    INDEX
    Explanations

    linguistic and grammatical markers

    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_65k_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
     креп
    0.48
     те
    0.43
    Де
    0.40
    О
    0.40
    れます
    0.40
    韪
    0.40
     удар
    0.39
    ходит
    0.39
     мат
    0.39
    см
    0.39
    POSITIVE LOGITS
    의
    0.66
    における
    0.63
    യിലെ
    0.61
    の
    0.61
    에서의
    0.61
    ിലെ
    0.58
     ਦੇ
    0.55
    的一些
    0.55
     edilen
    0.55
    lerin
    0.55
    Activations Density 0.021%

    No Known Activations