© 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. 62382
    Prev
    Next
    INDEX
    Explanations

    transition or change

    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
    fır
    -0.90
     ران
    -0.89
     продолжа
    -0.82
     continuation
    -0.82
    prnewswire
    -0.81
    גרפיה
    -0.79
    preduce
    -0.78
    diensten
    -0.78
     corações
    -0.78
    пен
    -0.74
    POSITIVE LOGITS
     went
    2.61
     from
    2.58
     transition
    2.52
     transitioning
    2.23
    从
    2.17
    transition
    2.02
     transitions
    1.98
    從
    1.96
     transitioned
    1.92
    Went
    1.91
    Activations Density 0.148%

    No Known Activations