© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55754
    Prev
    Next
    INDEX
    Explanations

    pass parameters and data

    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
    💱
    -0.75
    Răsp
    -0.74
     maybe
    -0.72
    hets
    -0.71
    =[];
    -0.71
    뭘
    -0.71
    umani
    -0.68
    Ⅽ
    -0.68
    guitarra
    -0.68
    畫
    -0.68
    POSITIVE LOGITS
     Excel
    1.30
     excel
    1.15
     testData
    1.11
    Excel
    1.09
    excel
    1.03
     sheet
    1.02
     data
    1.02
    Env
    1.01
     Test
    0.98
     Sheet
    0.98
    Activations Density 0.012%

    No Known Activations