© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 49358
    Prev
    Next
    INDEX
    Explanations

    emotions, mythology, Generation, feeling

    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
    ?
    0.54
    そして
    0.47
     интерфей
    0.46
     แล้ว
    0.46
    Brexit
    0.45
     Infrastructure
    0.45
    然后
    0.45
    쟁
    0.45
    Ви
    0.44
    想象
    0.44
    POSITIVE LOGITS
     devoting
    0.50
     Wochschr
    0.46
     psychiatrist
    0.45
     devote
    0.44
     psychiat
    0.44
     Hoffman
    0.44
     devotes
    0.43
     tenían
    0.43
     MBBS
    0.42
     biochem
    0.42
    Activations Density 0.029%

    No Known Activations