© 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. 16-GEMMASCOPE-2-RES-262K
    7. 17756
    Prev
    Next
    INDEX
    Explanations

    Queen chess piece

    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_16_width_262k_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
    :
    0.52
    ס
    0.44
    ،
    0.44
    :”
    0.43
    ARE
    0.43
     habilit
    0.42
    涿
    0.40
    .'
    0.40
     zalo
    0.40
    elt
    0.39
    POSITIVE LOGITS
     shine
    0.45
     metade
    0.44
    ቖ
    0.41
     semestre
    0.41
     સમયે
    0.41
    ião
    0.39
    is
    0.39
    紳
    0.39
    ljiv
    0.38
    ੀ
    0.38
    Activations Density 0.001%

    No Known Activations