© 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. 47171
    Prev
    Next
    INDEX
    Explanations

    am I asking questions

    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
     myself
    -1.04
     my
    -0.98
     it
    -0.96
     there
    -0.93
     meiner
    -0.88
     conmigo
    -0.81
     ive
    -0.80
     comigo
    -0.80
     мне
    -0.79
     Ive
    -0.79
    POSITIVE LOGITS
     I
    1.02
    живание
    0.88
    ಿ
    0.86
     eye
    0.80
     שע
    0.77
    шего
    0.76
     gustaría
    0.75
    ujú
    0.75
    月から
    0.75
    、「
    0.74
    Activations Density 0.017%

    No Known Activations