© 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. 52575
    Prev
    Next
    INDEX
    Explanations

    code definitions: class, struct, implementation

    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
    indahkan
    0.48
    で
    0.43
     бывает
    0.40
    urlopen
    0.40
     επισ
    0.40
     کولی
    0.39
     の
    0.39
    平和
    0.39
     поне
    0.38
    appara
    0.38
    POSITIVE LOGITS
     Aspects
    0.42
     száz
    0.42
     Malgré
    0.42
     Temperatures
    0.40
     Cruiser
    0.39
     Gorgeous
    0.39
     त्यानुसार
    0.39
     Bedrooms
    0.39
     Stylish
    0.38
     Temperature
    0.38
    Activations Density 0.001%

    No Known Activations