© 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. 20114
    Prev
    Next
    INDEX
    Explanations

    longer or larger comparison

    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
     zár
    0.43
     അവസാന
    0.41
    ഗ
    0.40
     preponder
    0.39
    ២
    0.39
     pintura
    0.39
     페이지
    0.39
    addition
    0.38
     zakoń
    0.38
     artik
    0.38
    POSITIVE LOGITS
    ML
    0.42
     خاصة
    0.41
    )][
    0.37
    TIM
    0.37
     Осо
    0.36
    峨
    0.36
    दाय
    0.36
    Ecc
    0.36
     осо
    0.35
     explained
    0.35
    Activations Density 0.001%

    No Known Activations