© 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. 1664
    Prev
    Next
    INDEX
    Explanations

    CPU utilization, GPU utilization

    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
     ασ
    0.43
    尾
    0.43
    ojen
    0.43
    抗
    0.42
    tail
    0.42
    razol
    0.41
    stion
    0.41
    τ
    0.41
     проб
    0.40
    Tail
    0.40
    POSITIVE LOGITS
     restaurante
    0.50
     BTW
    0.48
    hai
    0.47
    neux
    0.47
    உங்கள்
    0.46
     neighborhoods
    0.46
     cheerfully
    0.46
    ⟧
    0.45
    యు
    0.45
     declined
    0.45
    Activations Density 0.000%

    No Known Activations