© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130241
    Prev
    Next
    INDEX
    Explanations

    brand names or abbreviations

    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
    ־ה
    -1.56
    Größe
    -1.48
     there
    -1.43
     gedurende
    -1.36
     preescolar
    -1.33
     at
    -1.31
    pography
    -1.28
    .
    -1.27
    Fakta
    -1.24
     leur
    -1.23
    POSITIVE LOGITS
     your
    2.91
     you
    2.30
     these
    1.68
    anız
    1.54
    your
    1.47
     avulla
    1.42
     our
    1.41
    ándote
    1.28
    あなたが
    1.27
    <strong>
    1.26
    Activations Density 0.182%

    No Known Activations