© 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. 44574
    Prev
    Next
    INDEX
    Explanations

    defined by categories

    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
    ╩
    0.44
     липня
    0.44
     mysterious
    0.43
    詭
    0.43
    3
    0.42
     окру
    0.42
     unanimously
    0.42
    ወስ
    0.42
     facie
    0.41
    ೭
    0.41
    POSITIVE LOGITS
    ıklı
    0.43
     iklan
    0.42
     IP
    0.40
     DIP
    0.40
     Battery
    0.40
     Glance
    0.40
     acids
    0.39
     enk
    0.39
    rolyte
    0.38
     ưu
    0.38
    Activations Density 0.003%

    No Known Activations