© 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. 211672
    Prev
    Next
    INDEX
    Explanations

    been proposed

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

    young man or girl

    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
    Negative Logits
     solv
    0.46
     कॉ
    0.45
    ുമെന്ന്
    0.44
     ஓடுப
    0.43
     ऑस्ट्रेलियाई
    0.42
     வெளிப்புற
    0.42
     assail
    0.41
     Анали
    0.41
    凜
    0.41
     codebase
    0.40
    POSITIVE LOGITS
    ogar
    0.46
    shade
    0.44
    oceras
    0.42
     caoutchouc
    0.42
    want
    0.40
     jednoduch
    0.40
     품질
    0.40
    ijų
    0.39
    সাধন
    0.39
    銥
    0.39
    Activations Density 0.001%

    No Known Activations