© 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. 80806
    Prev
    Next
    INDEX
    Explanations

    how things feel

    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
    ppio
    -0.91
    ाइट
    -0.76
    रोध
    -0.75
     esfuer
    -0.73
    fx
    -0.73
    の姿
    -0.73
    пей
    -0.72
    tei
    -0.72
     Pflanze
    -0.71
    Subsystem
    -0.71
    POSITIVE LOGITS
     feel
    7.72
     feels
    7.44
     felt
    6.34
     feeling
    6.25
    feel
    5.97
    Feel
    5.81
     Feel
    5.78
     Feels
    5.28
    feels
    5.19
    feeling
    5.09
    Activations Density 0.198%

    No Known Activations