© 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. 48134
    Prev
    Next
    INDEX
    Explanations

    lists of cited names and publications

    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
     registrada
    -1.39
     schönes
    -1.36
    lju
    -1.32
     adecuados
    -1.31
     Vorteil
    -1.30
    泚
    -1.27
    strick
    -1.26
     extremamente
    -1.26
     encontrada
    -1.25
     naturlig
    -1.25
    POSITIVE LOGITS
     and
    1.70
     greco
    1.42
     fase
    1.33
     convento
    1.31
    modificar
    1.31
    led
    1.30
     were
    1.27
     precau
    1.27
    已有
    1.27
    <bos>
    1.25
    Activations Density 0.039%

    No Known Activations