© 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. 48712
    Prev
    Next
    INDEX
    Explanations

    defined states or actions

    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
     духо
    0.49
    AgentError
    0.48
    ອາຫານ
    0.48
     целей
    0.47
     관광
    0.47
    ᴙ
    0.47
    桨
    0.46
     راحت
    0.44
     Россию
    0.44
     каль
    0.44
    POSITIVE LOGITS
     Liter
    0.42
     Lire
    0.41
    sle
    0.40
     Now
    0.39
    ne
    0.39
     beob
    0.38
    h
    0.38
     Mond
    0.38
     Weg
    0.37
     constituer
    0.37
    Activations Density 0.009%

    No Known Activations