© 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. 46156
    Prev
    Next
    INDEX
    Explanations

    ) at offset

    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
    ير
    0.77
     classrooms
    0.70
     locais
    0.68
    局部
    0.68
    势力
    0.66
     mercados
    0.65
    二
    0.65
     pessoa
    0.65
    中间
    0.64
     Posteriormente
    0.64
    POSITIVE LOGITS
    ac
    0.75
    de
    0.72
    3
    0.71
     of
    0.69
    pore
    0.68
    list
    0.68
    ole
    0.67
    rence
    0.67
    use
    0.66
    standard
    0.66
    Activations Density 0.000%

    No Known Activations