© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93972
    Prev
    Next
    INDEX
    Explanations

    Make sure

    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
    設施
    -0.86
     available
    -0.75
    した場合
    -0.75
     ihres
    -0.73
    tomatik
    -0.73
     τι
    -0.73
    Venus
    -0.71
     الد
    -0.70
    満た
    -0.70
     approaches
    -0.69
    POSITIVE LOGITS
     your
    1.47
     plans
    1.20
    friends
    1.13
    plans
    1.09
     yourself
    1.06
     it
    1.05
     friends
    1.02
    计划
    0.95
    Plans
    0.92
     a
    0.91
    Activations Density 0.022%

    No Known Activations