© 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. 22-GEMMASCOPE-RES-131K
    7. 65821
    Prev
    Next
    INDEX
    Explanations

    Tag Archives:, Quantum Zeno, Q:

    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_22/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
     determinadas
    -0.91
     różnych
    -0.91
    tib
    -0.90
    manız
    -0.89
    oine
    -0.84
    polation
    -0.83
    lye
    -0.82
     fertig
    -0.81
     Fazit
    -0.81
     fuhr
    -0.81
    POSITIVE LOGITS
     besar
    1.04
    ælde
    0.99
     then
    0.93
     anormal
    0.91
    zionali
    0.89
    ówczas
    0.89
    чни
    0.89
     propor
    0.87
    用心
    0.85
     aswell
    0.84
    Activations Density 0.005%

    No Known Activations