© 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. 10-GEMMASCOPE-RES-131K
    7. 15278
    Prev
    Next
    INDEX
    Explanations

    transportation systems and security

    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_10/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
     '
    -2.55
    s
    -2.47
     varför
    -2.47
    ר
    -2.44
     当
    -2.25
    有一
    -2.22
     désir
    -2.19
    可以
    -2.17
    2
    -2.17
     такое
    -2.13
    POSITIVE LOGITS
    ,’
    3.22
    趼
    3.00
    姈
    2.78
    媗
    2.77
     vollständ
    2.75
    汭
    2.72
     trataba
    2.63
    煦
    2.58
    ݯ
    2.56
    贗
    2.56
    Activations Density 0.005%

    No Known Activations