© 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-262K
    7. 43311
    Prev
    Next
    INDEX
    Explanations

    completing a sentence

    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_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
     भेदभाव
    0.52
     их
    0.50
    heses
    0.49
     контроля
    0.48
     якая
    0.48
     исследований
    0.48
    푝
    0.47
    ását
    0.47
     Discrimination
    0.47
     jejich
    0.47
    POSITIVE LOGITS
    Avec
    0.48
    ar
    0.44
    Av
    0.44
    addr
    0.43
    garbage
    0.43
    ይ
    0.42
    castle
    0.42
     tormented
    0.42
     davon
    0.41
    ມີ
    0.41
    Activations Density 0.007%

    No Known Activations