© 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. 10-GEMMASCOPE-RES-131K
    7. 12911
    Prev
    Next
    INDEX
    Explanations

    contributed equally to

    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_10/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
    blurRadius
    -2.27
     atau
    -2.17
     alleged
    -1.98
    熒
    -1.98
    孭
    -1.97
     impressive
    -1.97
     impeccable
    -1.95
    AnchorStyles
    -1.92
     different
    -1.92
    ers
    -1.92
    POSITIVE LOGITS
    緜
    2.34
     the
    2.08
     contributed
    1.98
    ݯ
    1.96
     penyanyi
    1.96
    皛
    1.84
    我一直
    1.82
    蠵
    1.81
     Läs
    1.81
     participated
    1.77
    Activations Density 0.007%

    No Known Activations