© 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. 28274
    Prev
    Next
    INDEX
    Explanations

    businesses, email, complexity

    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
     ಮಾತ್ರ
    0.49
    ﻒ
    0.43
     hilfre
    0.43
    ﻪ
    0.41
    📒
    0.41
     hilfreich
    0.41
     በተጨማሪ
    0.41
    屻
    0.41
     duż
    0.41
     завжди
    0.41
    POSITIVE LOGITS
     from
    0.55
     China
    0.52
     to
    0.52
     inept
    0.52
     after
    0.50
     agent
    0.47
     vassal
    0.45
     от
    0.44
     आफ्टर
    0.44
     trading
    0.44
    Activations Density 0.008%

    No Known Activations