© 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. 118324
    Prev
    Next
    INDEX
    Explanations

    legal publication or articles

    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
    ALLOWED
    -0.75
    aclk
    -0.68
     сад
    -0.68
    干扰
    -0.67
    Напомним
    -0.67
    merate
    -0.66
    cka
    -0.66
     康
    -0.65
    simpan
    -0.65
     إلي
    -0.65
    POSITIVE LOGITS
    んだから
    0.71
    tiques
    0.68
     prom
    0.67
    ticias
    0.66
    esp
    0.66
    喚
    0.63
     enviar
    0.63
     кисло
    0.63
    atmosphere
    0.62
    tift
    0.62
    Activations Density 0.048%

    No Known Activations