© 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. 11511
    Prev
    Next
    INDEX
    Explanations

    listing and conjunctions

    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
    ed
    0.39
    chris
    0.38
    arka
    0.38
    d
    0.38
    োড
    0.37
    исленность
    0.37
     Startup
    0.37
    ဖို့
    0.37
    a
    0.37
    m
    0.36
    POSITIVE LOGITS
     valamint
    0.48
     respectively
    0.48
     እንዲሁም
    0.43
     respectivement
    0.42
    respectively
    0.42
     esprim
    0.41
     તેમજ
    0.40
     각각
    0.38
     그리고
    0.38
     તથા
    0.38
    Activations Density 0.005%

    No Known Activations