© 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. 102584
    Prev
    Next
    INDEX
    Explanations

    temperature outside

    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
     to
    -1.01
     junto
    -0.94
     it
    -0.93
     from
    -0.88
     that
    -0.87
     its
    -0.87
     problems
    -0.85
     aware
    -0.85
     suffering
    -0.84
     difficulties
    -0.81
    POSITIVE LOGITS
     outside
    3.05
    Outside
    2.42
    outside
    2.41
     Outside
    2.11
     afuera
    1.84
     OUTSIDE
    1.77
    OUTSIDE
    1.77
     draußen
    1.55
    外面
    1.48
     fuori
    1.41
    Activations Density 0.026%

    No Known Activations