© 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. 63450
    Prev
    Next
    INDEX
    Explanations

    imagine a scenario

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

    automatic answers

    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
    似乎
    0.48
    ﻠ
    0.47
    执
    0.46
    OrCallback
    0.46
    脸色
    0.46
    地产
    0.46
    Pergunta
    0.45
    દય
    0.44
     исход
    0.44
    回应
    0.44
    POSITIVE LOGITS
    jes
    0.50
    .
    0.49
     intestines
    0.48
     automatically
    0.48
     ancestors
    0.47
     enam
    0.47
     by
    0.46
     babies
    0.46
     padres
    0.45
     after
    0.45
    Activations Density 0.000%

    No Known Activations