© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23581
    Prev
    Next
    INDEX
    Explanations

    identification, Representative, license, ISBN

    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
     slant
    -0.85
    dide
    -0.84
    >*
    -0.79
     Dick
    -0.77
     Gear
    -0.77
     disintegration
    -0.74
     Dag
    -0.74
    slant
    -0.74
    erat
    -0.73
     bulletin
    -0.72
    POSITIVE LOGITS
     rebate
    0.80
    ắ
    0.79
     colleague
    0.78
     frontage
    0.78
    uca
    0.75
     manžel
    0.74
    ന്റെ
    0.73
     margarine
    0.72
    Liability
    0.72
    міністра
    0.72
    Activations Density 0.012%

    No Known Activations