© 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. 15557
    Prev
    Next
    INDEX
    Explanations

    reduce risk, avoid complications, save

    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
     несмотря
    -1.06
     despite
    -0.92
     Despite
    -0.83
     with
    -0.82
     to
    -0.80
     caveats
    -0.80
    wdriver
    -0.79
    才行
    -0.79
    🆚
    -0.78
     adequate
    -0.77
    POSITIVE LOGITS
    避免
    1.33
    Avoid
    1.24
     avoid
    1.22
    avoid
    1.20
     Avoid
    1.19
     evitar
    1.18
    elimin
    1.16
     Elimin
    1.13
    Elimin
    1.12
     save
    1.10
    Activations Density 0.097%

    No Known Activations