© 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. 48666
    Prev
    Next
    INDEX
    Explanations

    writing context

    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
    ارب
    0.39
     AVC
    0.39
     regulation
    0.39
     bilayers
    0.38
    BC
    0.38
    اث
    0.37
    심
    0.37
     laser
    0.36
     army
    0.36
    測
    0.36
    POSITIVE LOGITS
     ਵ
    0.58
    ूज
    0.54
     ഭക്ഷ
    0.53
    <unused1011>
    0.53
     स्थानीय
    0.52
     जोखिम
    0.50
     அவர்களின்
    0.50
    viel
    0.50
    onResume
    0.49
     живу
    0.49
    Activations Density 0.004%

    No Known Activations