© 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. 17000
    Prev
    Next
    INDEX
    Explanations

    Simple Components

    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
     som
    0.55
    ing
    0.50
    j
    0.48
     bru
    0.46
     bruising
    0.45
     B
    0.45
     D
    0.44
    getVisibility
    0.44
     والاست
    0.44
    মুখী
    0.43
    POSITIVE LOGITS
     사회
    0.54
    ゾ
    0.50
     учены
    0.49
     இயக்கு
    0.46
     economists
    0.45
     করিতেছিল
    0.45
     기업
    0.45
     parque
    0.44
     entrepreneurs
    0.44
     ಸಾಮಾ
    0.44
    Activations Density 0.002%

    No Known Activations