© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79348
    Prev
    Next
    INDEX
    Explanations

    names after numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    久し
    -2.09
    つづく
    -2.03
    来週
    -1.77
    にします
    -1.75
    明日は
    -1.74
    もうすぐ
    -1.73
    さぁ
    -1.71
    をしました
    -1.70
     gracioso
    -1.65
    すっ
    -1.63
    POSITIVE LOGITS
    は
    1.79
    も
    1.74
    が
    1.71
    と
    1.70
    を
    1.59
    などは
    1.55
    душка
    1.50
    香りが
    1.50
    つまり
    1.50
    があり
    1.46
    Activations Density 0.027%

    No Known Activations