© 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. 115542
    Prev
    Next
    INDEX
    Explanations

    calling something this

    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
    umumkan
    -1.19
     вони
    -1.09
    ITCHEN
    -1.05
     інших
    -1.05
    nicity
    -1.05
    ichtlich
    -1.02
    they
    -1.01
     cuando
    -1.00
     інші
    -1.00
    紘
    -0.98
    POSITIVE LOGITS
     it
    2.36
     them
    2.23
     this
    1.88
     him
    1.58
     these
    1.40
     each
    1.22
    current
    1.21
     the
    1.19
     us
    1.14
     themselves
    1.07
    Activations Density 0.069%

    No Known Activations