© 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. 107391
    Prev
    Next
    INDEX
    Explanations

    words ending in i or hi

    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
     dios
    -0.70
     campana
    -0.69
     requirements
    -0.69
     ه
    -0.69
    全新
    -0.69
     decret
    -0.68
    ятся
    -0.67
    分数
    -0.67
     Spots
    -0.66
    BeforeAll
    -0.66
    POSITIVE LOGITS
    onado
    0.79
    xX
    0.79
    laren
    0.78
    rót
    0.78
    즈
    0.77
    huit
    0.76
    Compl
    0.75
    ercicio
    0.74
     mám
    0.73
     However
    0.71
    Activations Density 0.036%

    No Known Activations