© 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. 40-GEMMASCOPE-2-RES-262K
    7. 109482
    Prev
    Next
    INDEX
    Explanations

    hashlib

    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_40_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
     Länge
    0.45
     length
    0.43
     læng
    0.43
     /*
    0.41
    Length
    0.41
    اريات
    0.39
     raindrops
    0.39
     vowels
    0.39
     diet
    0.39
     Length
    0.39
    POSITIVE LOGITS
     акы
    0.40
    ࣪
    0.40
    сіі
    0.38
    猷
    0.38
    
    0.38
     좋아요
    0.37
    유
    0.37
    oyu
    0.37
     Балт
    0.36
    遉
    0.36
    Activations Density 0.012%

    No Known Activations