© 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. 20748
    Prev
    Next
    INDEX
    Explanations

    true

    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
    t
    1.25
    ش
    0.81
    l
    0.80
    larda
    0.80
    ী
    0.80
    də
    0.79
    س
    0.79
    لها
    0.79
    ی
    0.79
    r
    0.78
    POSITIVE LOGITS
    1
    0.96
    8
    0.86
    2
    0.82
    ↵
    0.80
    7
    0.73
    iving
    0.68
    ript
    0.66
    3
    0.65
     is
    0.65
    iche
    0.64
    Activations Density 0.064%

    No Known Activations