© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 64616
    Prev
    Next
    INDEX
    Explanations

    communication, simulation, reporting, scan

    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
    αν
    0.42
    ਚ
    0.41
     upgrades
    0.41
     –
    0.40
     победи
    0.40
     سند
    0.40
    ل
    0.39
     optimised
    0.38
    🔑
    0.38
    投資
    0.38
    POSITIVE LOGITS
     obič
    0.47
     vitamina
    0.46
    剧
    0.45
     ढाई
    0.45
     विषा
    0.45
    ələ
    0.44
     पानी
    0.44
     dalje
    0.44
     leiden
    0.43
    픈
    0.43
    Activations Density 0.003%

    No Known Activations