© 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. 48042
    Prev
    Next
    INDEX
    Explanations

    labels and questions

    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
     of
    -1.42
     kanilang
    -1.04
     eorum
    -0.96
     their
    -0.91
    tituts
    -0.90
     dám
    -0.86
     ngunit
    -0.86
    لبوم
    -0.85
    czego
    -0.84
     informaci
    -0.84
    POSITIVE LOGITS
     is
    1.09
    也不
    0.88
    设置为
    0.87
    ぱ
    0.85
     referring
    0.84
     maupun
    0.84
     είναι
    0.83
     คือ
    0.83
    的说道
    0.82
     blazing
    0.82
    Activations Density 0.000%

    No Known Activations