© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 15765
    Prev
    Next
    INDEX
    Explanations

    sentence endings like です, ね, 요, ครับ

    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
     которого
    0.54
    </
    0.48
    "))
    0.48
    ");
    0.46
    을
    0.46
    كم
    0.45
    夗
    0.45
    就是
    0.45
    در
    0.44
     ataupun
    0.44
    POSITIVE LOGITS
    .+\
    0.44
    aneous
    0.43
    ur
    0.42
    INTRODUCTION
    0.41
     會
    0.41
    gerufen
    0.41
    .}~\
    0.41
     মহাশ
    0.40
    ๑
    0.40
    yielding
    0.40
    Activations Density 0.004%

    No Known Activations