© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107355
    Prev
    Next
    INDEX
    Explanations

    lest, least, else

    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_34/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
    "])
    -0.87
    azol
    -0.82
    ulo
    -0.82
    andolo
    -0.82
    )];
    -0.80
     tecnologie
    -0.80
    рных
    -0.78
    cbo
    -0.78
    ھا
    -0.78
     erklären
    -0.77
    POSITIVE LOGITS
     lest
    6.31
    lest
    4.28
     Lest
    3.61
     least
    2.38
    以免
    2.30
    Least
    1.91
     else
    1.77
     leste
    1.72
     Least
    1.69
    least
    1.60
    Activations Density 0.032%

    No Known Activations