© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35483
    Prev
    Next
    INDEX
    Explanations

    duties and obligations

    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
     only
    -1.56
     just
    -1.36
     then
    -1.30
     after
    -1.30
     more
    -1.27
     now
    -1.27
     already
    -1.18
     want
    -1.15
     our
    -1.14
     still
    -1.13
    POSITIVE LOGITS
    錾
    1.37
    must
    1.20
    launched
    1.19
    ⁉
    1.17
     любые
    1.17
    particularly
    1.17
    🧐
    1.16
    甶
    1.16
    ఽ
    1.16
    
    1.13
    Activations Density 0.003%

    No Known Activations