© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27488
    Prev
    Next
    INDEX
    Explanations

    code comments and syntax

    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
     serão
    0.51
     olhos
    0.47
     saranno
    0.46
    aya
    0.44
     о
    0.44
     подска
    0.43
     probabilidades
    0.43
    ati
    0.43
    都知道
    0.43
     будут
    0.42
    POSITIVE LOGITS
    ᅦ
    0.46
    ार्ज
    0.44
     විශේෂ
    0.44
    selt
    0.41
    ﻌ
    0.40
    </em>
    0.39
     ප්‍ර
    0.39
     benches
    0.38
     researcher
    0.38
     structural
    0.38
    Activations Density 0.002%

    No Known Activations