© 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. 76379
    Prev
    Next
    INDEX
    Explanations

    ice, frost, cold

    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
     sufrimiento
    -0.75
     寶
    -0.75
    埴
    -0.73
    htä
    -0.71
     unintentional
    -0.70
    exprimer
    -0.70
    ائدة
    -0.69
     протяжении
    -0.69
    fiz
    -0.68
     Berührung
    -0.68
    POSITIVE LOGITS
    Freeze
    1.13
    Frozen
    1.09
     Freeze
    1.03
     Frozen
    0.99
    Ice
    0.99
    🧊
    0.94
     Artic
    0.91
    冻
    0.91
    冷
    0.90
    凍
    0.90
    Activations Density 0.017%

    No Known Activations