© 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. 14421
    Prev
    Next
    INDEX
    Explanations

    critical examination

    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
    simum
    -0.89
    狈
    -0.89
    ipot
    -0.89
     svært
    -0.87
    écou
    -0.86
     problemática
    -0.85
    ాయ
    -0.85
     пей
    -0.84
    islamic
    -0.84
    ignor
    -0.83
    POSITIVE LOGITS
     scrutiny
    1.55
     scrutin
    1.48
     questioning
    1.16
     checking
    1.13
     examination
    1.13
     rigorous
    1.12
    scr
    1.08
     thorough
    1.07
     testing
    1.07
     examinations
    1.06
    Activations Density 0.066%

    No Known Activations