© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37288
    Prev
    Next
    INDEX
    Explanations

    lyrics, sleep, cosmic, googling

    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_262k_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
     existencia
    0.43
     existência
    0.43
    Could
    0.41
    .
    0.41
    ៅ
    0.41
     thérapeut
    0.40
    搜
    0.40
    ជាមួយនឹង
    0.39
     SEQ
    0.39
    回到
    0.39
    POSITIVE LOGITS
    กลาง
    0.52
    IGAN
    0.49
    ोरेशन
    0.49
    IDO
    0.47
    κος
    0.47
    িয়৷
    0.47
    IDGE
    0.46
    ेलकम
    0.46
     sleep
    0.45
    ピアス
    0.45
    Activations Density 0.001%

    No Known Activations