Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 1665
    Prev
    Next
    INDEX
    Explanations

    how actions are done

    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_40_width_262k_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
     thereof
    0.21
     lambda
    0.19
     /,
    0.18
     varphi
    0.18
    זו
    0.18
     dec
    0.17
     umbrella
    0.17
    кову
    0.17
     Hamming
    0.17
     ^{
    0.17
    POSITIVE LOGITS
     casually
    0.25
     separately
    0.24
     comfortably
    0.22
     liberally
    0.21
    圿
    0.21
     ফেলতে
    0.21
    áférés
    0.21
     Wojcie
    0.21
     differently
    0.20
     meaningfully
    0.20
    Activations Density 0.067%

    No Known Activations