© 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. 5503
    Prev
    Next
    INDEX
    Explanations

    introducing phrases and multilingual words

    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
    ڦ
    0.29
    فو
    0.28
    فك
    0.28
    ﮏ
    0.28
    Notification
    0.27
    𝗅
    0.26
    <0xF3>
    0.26
    یک
    0.25
    වා
    0.25
    كز
    0.25
    POSITIVE LOGITS
     більш
    0.30
     там
    0.29
    そして
    0.29
    有一些
    0.29
     همچنین
    0.28
     هناك
    0.28
     And
    0.28
     there
    0.27
     sadly
    0.27
     מאוד
    0.27
    Activations Density 0.249%

    No Known Activations