© 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. 106351
    Prev
    Next
    INDEX
    Explanations

    common cache

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

    contrast, qualification, or description

    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
    ALS
    0.54
    ERCISE
    0.48
    RestorePolicy
    0.47
    기를
    0.45
     implicate
    0.45
    als
    0.43
    佯
    0.43
    ᕈ
    0.41
    ОР
    0.40
    翮
    0.40
    POSITIVE LOGITS
     étaient
    0.49
     beliau
    0.47
    ंबई
    0.45
     swój
    0.45
     SEO
    0.44
     Italia
    0.44
     verdens
    0.44
     város
    0.44
     Vocês
    0.44
     为了
    0.44
    Activations Density 0.000%

    No Known Activations