© 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. 67043
    Prev
    Next
    INDEX
    Explanations

    confidential or private information

    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
     Walkover
    -0.84
     UNT
    -0.81
     tưởng
    -0.80
     aureus
    -0.78
     bici
    -0.75
    magitan
    -0.75
     tass
    -0.74
    ⋈
    -0.74
    uVar
    -0.74
     bacterio
    -0.74
    POSITIVE LOGITS
     confidential
    1.62
     Confidential
    1.13
    Confidential
    1.06
     private
    1.02
     proprietary
    1.02
    private
    0.97
     confidentiality
    0.95
    Privacy
    0.89
    Private
    0.87
    sensitive
    0.86
    Activations Density 0.067%

    No Known Activations