© 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-262K
    7. 3304
    Prev
    Next
    INDEX
    Explanations

    at the

    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
     heeft
    0.44
     llamado
    0.41
     Ahora
    0.41
     kêu
    0.41
    蹒
    0.40
    还在
    0.40
    嘶
    0.39
    
    0.39
     llam
    0.39
     zahlreiche
    0.39
    POSITIVE LOGITS
     later
    0.44
     afterward
    0.42
     eventually
    0.42
     derived
    0.41
     eventual
    0.41
     любых
    0.40
    ท้าย
    0.39
     nantinya
    0.39
     bounty
    0.38
    더라구요
    0.38
    Activations Density 0.023%

    No Known Activations