© 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. 109122
    Prev
    Next
    INDEX
    Explanations

    commits illegal actions

    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
     eventually
    -0.89
    kuwa
    -0.85
     that
    -0.82
     mindig
    -0.81
     complying
    -0.79
     maybe
    -0.79
    在这里
    -0.77
     encontrou
    -0.77
     rapporti
    -0.77
     decidió
    -0.77
    POSITIVE LOGITS
     knowingly
    1.61
     attempt
    1.15
     engage
    1.12
    GEBRA
    1.10
    know
    1.07
     intentionally
    1.03
     assist
    1.02
    attempt
    1.01
    cept
    1.00
    intention
    0.99
    Activations Density 0.033%

    No Known Activations