© 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. 192618
    Prev
    Next
    INDEX
    Explanations

    credit, badge, billion, pieces

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

    running LLMs on CPUs

    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
    💹
    0.46
     cosmopolitan
    0.45
     prestación
    0.44
    㱛
    0.44
    Medi
    0.43
    முறை
    0.43
     Rashifal
    0.43
     Notiflix
    0.43
    砊
    0.43
    ণ্য
    0.43
    POSITIVE LOGITS
    angles
    0.46
     anchors
    0.46
    از
    0.45
    ट्ट
    0.44
    رت
    0.44
    attered
    0.44
    amboat
    0.44
    ("../../
    0.43
    deleg
    0.43
    trust
    0.43
    Activations Density 0.001%

    No Known Activations