© 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. 107022
    Prev
    Next
    INDEX
    Explanations

    words starting with "to"

    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
    r
    -0.88
    m
    -0.83
     свою
    -0.81
    ですが
    -0.80
    现在
    -0.79
    ？？
    -0.78
     systém
    -0.77
    と
    -0.75
    re
    -0.75
    f
    -0.75
    POSITIVE LOGITS
    toise
    1.18
     whom
    1.17
     jedno
    0.98
    らを
    0.95
    onto
    0.95
     vormen
    0.94
    ombs
    0.94
     opérateur
    0.93
    toe
    0.93
    したこと
    0.93
    Activations Density 0.054%

    No Known Activations