© 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. 26113
    Prev
    Next
    INDEX
    Explanations

    various

    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
    𓁹
    -3.11
    踯
    -2.64
     trois
    -2.61
    骉
    -2.48
     specif
    -2.45
    𖣔
    -2.38
     😁
    -2.36
    푆
    -2.33
    eſ
    -2.30
     térmica
    -2.22
    POSITIVE LOGITS
    各样的
    2.95
     There
    2.78
     Surprisingly
    2.56
     Their
    2.55
     Bringing
    2.50
     Here
    2.48
     aspects
    2.44
     Taking
    2.39
     multifaceted
    2.39
     promotes
    2.38
    Activations Density 0.025%

    No Known Activations