© 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. 103603
    Prev
    Next
    INDEX
    Explanations

    organizations and positions

    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
     distanza
    -1.33
    ۀ
    -1.15
     Antivirus
    -1.15
    YS
    -1.13
     migliorare
    -1.13
     Шаг
    -1.13
    そんなに
    -1.13
     excitedly
    -1.12
     incluye
    -1.11
    隳
    -1.09
    POSITIVE LOGITS
     حتی
    1.23
    These
    1.20
    </h3>
    1.20
    rifle
    1.15
    Still
    1.08
    :{
    1.08
     Anglican
    1.08
     ""));
    1.08
    Even
    1.05
     flesta
    1.05
    Activations Density 0.112%

    No Known Activations