© 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. 74645
    Prev
    Next
    INDEX
    Explanations

    tight, tightened, tightest

    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
    ↵
    -1.91
     Brought
    -1.77
     Allowing
    -1.73
     immense
    -1.67
    {
    -1.65
     “
    -1.65
     Placing
    -1.64
    ↵↵
    -1.63
     durante
    -1.62
     Otras
    -1.62
    POSITIVE LOGITS
    tight
    2.42
    嗵
    2.02
     tight
    1.94
    蟜
    1.91
    茕
    1.88
    虯
    1.88
     démocr
    1.86
     tightened
    1.85
     produkter
    1.85
     یا
    1.84
    Activations Density 0.016%

    No Known Activations