© 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. 7274
    Prev
    Next
    INDEX
    Explanations

    unsigned char

    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
     USA
    -0.83
    莞
    -0.75
    Transcriptie
    -0.74
     odpowied
    -0.73
    וכ
    -0.72
     proved
    -0.71
     Might
    -0.71
    ང
    -0.70
    rscheinlich
    -0.69
     종
    -0.69
    POSITIVE LOGITS
     結婚
    0.90
     JpaRepository
    0.86
    ifflin
    0.83
     contrase
    0.81
     Polite
    0.80
    Сообщение
    0.80
     Ibis
    0.79
     huevos
    0.79
     poliester
    0.79
    hosp
    0.79
    Activations Density 0.005%

    No Known Activations