© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33450
    Prev
    Next
    INDEX
    Explanations

    classifications and service history

    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
     will
    -1.28
     an
    -1.24
     your
    -1.20
     this
    -1.18
     should
    -1.17
     every
    -1.06
     each
    -1.05
     our
    -0.97
    ])->
    -0.96
    onBackPressed
    -0.93
    POSITIVE LOGITS
     guadag
    1.23
    眉头
    1.14
    慑
    1.13
    
    1.10
    主な
    1.06
    burgers
    1.06
    的那种
    1.06
    especially
    1.05
    terre
    1.04
    屐
    1.02
    Activations Density 0.052%

    No Known Activations