© 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. 118539
    Prev
    Next
    INDEX
    Explanations

    structuring text with labels

    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
     each
    -1.06
    每個
    -0.81
    Each
    -0.80
    غو
    -0.78
    🐦
    -0.77
    Delta
    -0.75
    uker
    -0.75
    nungs
    -0.75
     ciascuno
    -0.74
     Each
    -0.73
    POSITIVE LOGITS
    umbing
    0.84
     per
    0.81
     commons
    0.78
    Volver
    0.76
    Saul
    0.73
     التواصل
    0.73
    adop
    0.72
     Григо
    0.72
     Каза
    0.71
    Clima
    0.71
    Activations Density 0.015%

    No Known Activations