© 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. 34-GEMMASCOPE-RES-131K
    4. 59903
    Prev
    Next
    INDEX
    Explanations

    current subject matter constraints

    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
    illette
    -0.93
    ってみて
    -0.90
     scold
    -0.87
     bosque
    -0.84
    vues
    -0.83
     sucedió
    -0.83
    wym
    -0.82
    зык
    -0.82
     ingles
    -0.82
     cómod
    -0.82
    POSITIVE LOGITS
     lietu
    1.03
    Fk
    0.88
    sedown
    0.84
    jgl
    0.81
    ާ
    0.80
     ウッド
    0.79
     dessins
    0.77
     jemals
    0.75
    defi
    0.75
     relati
    0.75
    Activations Density 0.001%

    No Known Activations