© 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-65K
    4. 313
    Prev
    Next
    INDEX
    Explanations

    utf-8

    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
    <unused1080>
    0.25
    িগ্ন
    0.24
    <unused2020>
    0.22
    訨
    0.22
     Và
    0.21
    竰
    0.21
    羵
    0.21
     entsprechen
    0.21
    <unused1149>
    0.21
    ।”
    0.21
    POSITIVE LOGITS
     be
    0.23
    3
    0.20
     prime
    0.19
      
    0.19
     one
    0.19
     ra
    0.18
    s
    0.18
    G
    0.18
     winds
    0.17
            
    0.17
    Activations Density 0.000%

    No Known Activations