© 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. 47356
    Prev
    Next
    INDEX
    Explanations

    medium.com articles

    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
    (=)
    -0.78
    mW
    -0.75
    gm
    -0.72
    itto
    -0.71
     estou
    -0.69
    antz
    -0.66
    ącz
    -0.66
    otros
    -0.66
    \}.
    -0.66
    𝙞
    -0.64
    POSITIVE LOGITS
     tipi
    0.84
     Toys
    0.81
    Titel
    0.80
    Cardio
    0.76
    şu
    0.75
    今
    0.75
     MBE
    0.74
    bitro
    0.74
     clapped
    0.74
     ventana
    0.73
    Activations Density 0.004%

    No Known Activations