© 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. 56865
    Prev
    Next
    INDEX
    Explanations

    non-disclosure agreements

    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
    pores
    0.50
    ያንዳ
    0.49
    czną
    0.49
     ಎಲ್ಲಾ
    0.49
     getpath
    0.48
    populations
    0.47
     সম্ভাবনা
    0.47
    =[],
    0.46
    منی
    0.46
    directions
    0.46
    POSITIVE LOGITS
     staggering
    0.53
     stagger
    0.52
     Union
    0.47
     Scotia
    0.46
     Coles
    0.46
    chet
    0.44
     Seattle
    0.44
    챌
    0.43
    та
    0.43
     marital
    0.43
    Activations Density 0.005%

    No Known Activations