© 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. 66802
    Prev
    Next
    INDEX
    Explanations

    what is and how

    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
    ždy
    -1.11
     Himself
    -1.01
    sipasi
    -0.99
     případě
    -0.95
    gnose
    -0.94
    kiej
    -0.91
     actually
    -0.91
     スニーカー
    -0.91
    ']}
    -0.89
     truly
    -0.88
    POSITIVE LOGITS
     its
    2.08
     how
    1.75
     why
    1.36
    its
    1.13
     it
    1.12
     origins
    1.09
    它的
    1.05
    how
    1.02
     How
    1.02
    Its
    1.02
    Activations Density 0.102%

    No Known Activations