© 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. 22-GEMMASCOPE-RES-131K
    7. 70528
    Prev
    Next
    INDEX
    Explanations

    project start

    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_22/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
     today
    -1.16
     dedicar
    -1.08
     according
    -1.08
    Égypte
    -1.05
     جدید
    -1.02
     yesterday
    -1.01
    ListTile
    -0.96
    ఁ
    -0.96
     themselves
    -0.95
     تازه
    -0.94
    POSITIVE LOGITS
     project
    1.42
     was
    1.38
     projects
    1.13
    projectName
    1.12
    prj
    1.07
    だったが
    1.07
     был
    1.02
     Krankheiten
    1.02
     где
    1.00
     spesso
    1.00
    Activations Density 0.060%

    No Known Activations