© 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. 184947
    Prev
    Next
    INDEX
    Explanations

    to the extent that

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

    contrasting perspectives

    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
    reate
    0.46
     bois
    0.43
    ्य
    0.42
     綿
    0.42
    filepath
    0.41
     vadd
    0.41
    AMENT
    0.41
     mais
    0.40
     starost
    0.40
    review
    0.39
    POSITIVE LOGITS
     displayNumber
    0.46
     जबर
    0.43
    喈
    0.42
    称为
    0.41
    它
    0.41
    Derivative
    0.40
    的结果
    0.40
    不仅
    0.40
    多多
    0.39
    姮
    0.39
    Activations Density 0.002%

    No Known Activations