© 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. 5089
    Prev
    Next
    INDEX
    Explanations

    falafel

    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
     Від
    0.38
     Hü
    0.37
     Wall
    0.36
     Singles
    0.35
    Wall
    0.35
     başlayan
    0.34
     Nuovo
    0.34
    噪
    0.33
     jewellery
    0.33
    Noise
    0.33
    POSITIVE LOGITS
     persones
    0.40
    vil
    0.38
     inequities
    0.37
     meminta
    0.37
    үкт
    0.37
     psor
    0.37
    ණ්ඩ
    0.37
     healthful
    0.37
    ább
    0.36
     médec
    0.35
    Activations Density 0.000%

    No Known Activations