© 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. 34-GEMMASCOPE-RES-131K
    7. 119181
    Prev
    Next
    INDEX
    Explanations

    ice cream

    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
    Senegal
    -0.72
    Riz
    -0.71
    Исто
    -0.71
    ALU
    -0.70
    잡
    -0.69
    composite
    -0.69
     vestido
    -0.69
    diagnosis
    -0.68
    hero
    -0.68
     Langen
    -0.68
    POSITIVE LOGITS
     cream
    5.53
     Cream
    4.06
    cream
    3.95
    Cream
    3.78
     CREAM
    3.23
     creams
    2.94
    クリーム
    2.66
     creamy
    2.66
     creme
    2.39
     crème
    2.25
    Activations Density 0.040%

    No Known Activations