© 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. 30236
    Prev
    Next
    INDEX
    Explanations

    introducing a contrast

    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
    Not in Any Lists

    No Comments

    Negative Logits
    довой
    -0.82
     perennial
    -0.80
     hitherto
    -0.79
    enerbahçe
    -0.76
     keluarga
    -0.74
    techniques
    -0.73
     visar
    -0.73
    かした
    -0.73
     raio
    -0.72
    ্য
    -0.72
    POSITIVE LOGITS
    ><
    0.89
    Anybody
    0.86
     fills
    0.83
    edy
    0.82
     Bakterien
    0.81
    Wouldn
    0.80
    크
    0.79
    žu
    0.78
    Shouldn
    0.78
     welcomes
    0.77
    Activations Density 0.009%

    No Known Activations