© 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. 170081
    Prev
    Next
    INDEX
    Explanations

    common phrases and structures

    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
    鉉
    0.54
    ᅴ
    0.52
    㑹
    0.52
    秞
    0.52
    仍然
    0.50
    甴
    0.48
     Chao
    0.47
     Riccardo
    0.47
     Bài
    0.47
    🇽
    0.46
    POSITIVE LOGITS
     створе
    0.57
     accounts
    0.46
     organisms
    0.45
     çıkarm
    0.45
     tables
    0.43
    ortion
    0.43
     kebij
    0.43
     rewards
    0.42
     вслед
    0.42
     algal
    0.41
    Activations Density 0.000%

    No Known Activations