© 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. 4995
    Prev
    Next
    INDEX
    Explanations

    relationships and connections

    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
    檸
    0.38
    VIDIA
    0.38
     ମ
    0.38
    нтэр
    0.35
    Twig
    0.35
    ктор
    0.35
     TEA
    0.34
    ُم
    0.33
     க
    0.32
     곡
    0.32
    POSITIVE LOGITS
     '../
    0.40
     other
    0.39
     предыду
    0.39
     previous
    0.38
     connect
    0.38
     जडेजा
    0.37
     விரி
    0.37
    攝
    0.36
    existing
    0.35
    ness
    0.35
    Activations Density 0.000%

    No Known Activations