© 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. 20631
    Prev
    Next
    INDEX
    Explanations

    introductions and explanations

    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
    ။
    0.57
    nBitCount
    0.57
     그죠
    0.51
    BindView
    0.50
     ແລະ
    0.50
     হানি
    0.50
     আৰু
    0.49
     そして
    0.49
    ampaikan
    0.49
    ementara
    0.49
    POSITIVE LOGITS
    im
    0.51
     can
    0.48
    ة
    0.47
    i
    0.46
    ing
    0.46
    ab
    0.46
    itt
    0.46
    ين
    0.45
    il
    0.45
    te
    0.45
    Activations Density 0.045%

    No Known Activations