© 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. 34-GEMMASCOPE-RES-131K
    7. 57695
    Prev
    Next
    INDEX
    Explanations

    names, numbers, and technical terms

    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_34/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
    cessite
    -0.79
    シブル
    -0.71
     空港
    -0.70
    ⠴
    -0.70
     slept
    -0.68
    삽
    -0.68
    errMsg
    -0.67
     dů
    -0.66
    װ
    -0.66
     onerous
    -0.66
    POSITIVE LOGITS
     receta
    0.85
     hề
    0.84
     breaker
    0.83
     formulas
    0.82
     macro
    0.82
     masa
    0.81
     harga
    0.78
    AAT
    0.78
     Enduro
    0.78
    ragment
    0.78
    Activations Density 0.024%

    No Known Activations