© 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. 94013
    Prev
    Next
    INDEX
    Explanations

    of which

    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
     very
    -1.14
     even
    -1.09
    猖
    -1.07
     grasas
    -1.06
     especially
    -1.05
     mView
    -1.04
     so
    -1.02
    >\<^
    -1.00
     sentada
    -0.98
     for
    -0.97
    POSITIVE LOGITS
     of
    6.03
    Of
    2.86
     Of
    2.84
    of
    2.48
     whereof
    2.41
    うち
    2.38
    其中
    2.34
     của
    2.30
    ของ
    2.27
    のうち
    1.95
    Activations Density 0.155%

    No Known Activations