© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 173837
    Prev
    Next
    INDEX
    Explanations

    or their, rig are, pets if, joint vent

    np_acts-logits-general · gemini-2.5-flash-lite

    explanations and clarifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    会计
    0.45
    अप्रैल
    0.43
    작가
    0.42
    凤
    0.42
    궜
    0.42
    Benchmark
    0.41
     நான்கு
    0.41
    牛仔
    0.41
    кратно
    0.41
     יכול
    0.41
    POSITIVE LOGITS
    0.47
    來看一下
    0.44
    っぽい
    0.42
     ecco
    0.41
    nt
    0.40
    って
    0.40
    ík
    0.40
     n
    0.39
     probably
    0.39
     Somehow
    0.39
    Activations Density 0.001%

    No Known Activations