© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63650
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming terms

    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
     Flower
    -0.76
    ǃ
    -0.75
     tanah
    -0.74
     Frankrijk
    -0.74
    waite
    -0.73
    Axios
    -0.73
    eren
    -0.73
     RATE
    -0.72
    通過
    -0.71
     kalın
    -0.71
    POSITIVE LOGITS
     factoring
    0.82
    iqué
    0.79
    libc
    0.77
     Shanks
    0.74
     searched
    0.74
     kang
    0.74
     recover
    0.73
     expected
    0.73
    صح
    0.73
    cestors
    0.73
    Activations Density 0.045%

    No Known Activations