© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52241
    Prev
    Next
    INDEX
    Explanations

    medical/software/math terms

    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
    🥙
    0.45
    🛴
    0.44
    🤜
    0.43
    )+
    0.41
    👳
    0.41
    이
    0.40
     enggak
    0.40
    👥
    0.40
    ↵↵↵↵↵↵↵↵↵↵
    0.39
     diss
    0.39
    POSITIVE LOGITS
     coincid
    0.42
     precau
    0.41
     succinct
    0.40
     basit
    0.40
     penultimate
    0.40
     cautious
    0.40
    浗
    0.39
     کننده
    0.39
     concise
    0.39
     circum
    0.38
    Activations Density 0.003%

    No Known Activations