© 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. 36162
    Prev
    Next
    INDEX
    Explanations

    constant velocity

    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
     testers
    0.46
    socks
    0.43
    popen
    0.43
    缃
    0.41
    vocals
    0.41
    حق
    0.41
    untut
    0.40
    testers
    0.40
    filters
    0.40
     اسمبلی
    0.40
    POSITIVE LOGITS
    }\
    0.47
     mother
    0.45
     різних
    0.44
     こと
    0.44
     combina
    0.43
    と呼ばれる
    0.43
    として
    0.42
     你
    0.42
    と呼ば
    0.42
     různých
    0.41
    Activations Density 0.039%

    No Known Activations