© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4269
    Prev
    Next
    INDEX
    Explanations

    person names and labels

    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_16_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
    ’
    0.36
    ik
    0.34
    研究
    0.32
     رکھتے
    0.30
    ut
    0.30
    produktion
    0.30
    ra
    0.29
    ри
    0.29
    ushchev
    0.28
     naprawdę
    0.28
    POSITIVE LOGITS
     be
    0.31
     but
    0.30
    지
    0.30
     sobbing
    0.29
     muffled
    0.29
     tranquil
    0.29
     commotion
    0.28
     urine
    0.28
     mound
    0.28
     dusk
    0.27
    Activations Density 1.113%

    No Known Activations