© 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-65K
    7. 2440
    Prev
    Next
    INDEX
    Explanations

    prepositions or locative words

    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
     styling
    0.46
    ্যেষ্ঠ
    0.42
     rebranding
    0.41
     positioning
    0.39
     Piece
    0.39
    ثیر
    0.39
     celebración
    0.39
    괵
    0.39
     "_
    0.38
     Fragment
    0.38
    POSITIVE LOGITS
     kwenye
    1.10
     în
    1.06
     katika
    1.05
    ใน
    1.01
     në
    0.94
     ở
    0.93
     dalam
    0.91
     في
    0.91
     във
    0.91
     στην
    0.88
    Activations Density 0.378%

    No Known Activations