© 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. 118076
    Prev
    Next
    INDEX
    Explanations

    words starting with cri

    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
    Ответить
    -0.77
    多种
    -0.73
    Moe
    -0.72
    冲突
    -0.71
    werve
    -0.71
     Leia
    -0.70
    Harriet
    -0.70
     irritation
    -0.70
    ペース
    -0.69
    ള്
    -0.69
    POSITIVE LOGITS
    Cri
    1.39
     cri
    1.38
     Cri
    1.31
    cri
    0.99
     кри
    0.94
     Crim
    0.85
    кри
    0.82
    mean
    0.81
     criticised
    0.81
    Кри
    0.79
    Activations Density 0.032%

    No Known Activations