© 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. 58910
    Prev
    Next
    INDEX
    Explanations

    documentation and other materials

    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
    modify
    -0.72
     guarantee
    -0.71
     funcionamento
    -0.70
    ">&
    -0.69
     getView
    -0.68
     coming
    -0.67
    ällor
    -0.66
     Pelican
    -0.66
     ܝ
    -0.65
    ängerin
    -0.65
    POSITIVE LOGITS
     zato
    0.76
    ะ
    0.72
    ACI
    0.65
     infusion
    0.65
    luğu
    0.64
    リューム
    0.63
     electrified
    0.63
    duty
    0.63
     وط
    0.63
    ̛
    0.61
    Activations Density 0.084%

    No Known Activations