© 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. 10-GEMMASCOPE-RES-131K
    7. 127494
    Prev
    Next
    INDEX
    Explanations

    numbers containing decimals

    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
    yled
    -1.47
    但是
    -1.33
    wigs
    -1.32
    ־ה
    -1.28
    wość
    -1.27
    lised
    -1.27
    هر
    -1.27
    xffff
    -1.24
    manned
    -1.24
    жка
    -1.22
    POSITIVE LOGITS
     '
    1.47
    </strong>
    1.39
     sabias
    1.37
     связанные
    1.35
    Vendredi
    1.29
    優しく
    1.27
     verdaderamente
    1.27
     aislados
    1.27
    Contexte
    1.26
    逦
    1.25
    Activations Density 0.032%

    No Known Activations