© 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. 38744
    Prev
    Next
    INDEX
    Explanations

    opening after selection

    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
    filosof
    -0.83
    enservice
    -0.81
     设计
    -0.79
     позиции
    -0.79
    arri
    -0.79
    irdre
    -0.79
     ornate
    -0.78
    なかなか
    -0.78
     vat
    -0.77
    ጡ
    -0.77
    POSITIVE LOGITS
     after
    1.12
    goto
    1.06
     goto
    1.05
     transfer
    1.02
     exit
    0.94
     leave
    0.90
     go
    0.89
     went
    0.85
     redirect
    0.83
     preparing
    0.83
    Activations Density 0.018%

    No Known Activations