© 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. 115742
    Prev
    Next
    INDEX
    Explanations

    managed service

    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
    . 
    -0.76
    ionista
    -0.76
    HEADER
    -0.71
    Endereço
    -0.70
    newVal
    -0.69
    tividad
    -0.68
     Ihm
    -0.68
     skjø
    -0.68
     mcdonald
    -0.68
    idden
    -0.67
    POSITIVE LOGITS
     campsites
    0.75
    posterous
    0.74
    酸化
    0.73
     Campos
    0.72
    boca
    0.71
    殇
    0.69
     Truth
    0.68
    大切に
    0.67
     campsite
    0.66
    RESPONS
    0.66
    Activations Density 0.039%

    No Known Activations