© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35453
    Prev
    Next
    INDEX
    Explanations

    Q: or // or

    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
    EventArgs
    -1.09
    uransi
    -1.03
    melen
    -1.00
     Maggiore
    -0.97
     September
    -0.97
    ESG
    -0.96
    NEM
    -0.94
    ˝
    -0.93
    springs
    -0.93
     concurso
    -0.92
    POSITIVE LOGITS
     freaking
    1.02
     invece
    0.94
     and
    0.93
     freakin
    0.93
    為に
    0.92
    未だ
    0.91
    other
    0.91
     similarly
    0.91
    色々と
    0.91
    でお
    0.90
    Activations Density 0.000%

    No Known Activations