© 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. 94112
    Prev
    Next
    INDEX
    Explanations

    Purification and fixtures

    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
     máis
    -0.83
     kunjungan
    -0.81
    Ẩ
    -0.78
     eines
    -0.78
     moonlight
    -0.77
    cris
    -0.77
     zur
    -0.76
     yaklaşık
    -0.76
    nein
    -0.75
     Enamel
    -0.75
    POSITIVE LOGITS
     photo
    1.20
     content
    1.11
     photos
    1.09
    Photo
    1.09
    Content
    1.06
    photo
    1.04
    IFICATIONS
    1.00
    FOLLOW
    0.96
    Source
    0.96
    ὺς
    0.93
    Activations Density 0.004%

    No Known Activations