© 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. 65587
    Prev
    Next
    INDEX
    Explanations

    lively nightlife atmosphere

    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
    recursive
    -0.84
    icium
    -0.81
    iewicz
    -0.78
    ພ
    -0.77
    Lähde
    -0.77
    zęd
    -0.77
    atory
    -0.76
    رحلة
    -0.75
     stanza
    -0.75
     Voyage
    -0.75
    POSITIVE LOGITS
     lively
    2.53
     vibrant
    2.38
     nightlife
    2.13
    vibr
    2.09
     vib
    2.05
     vibe
    1.80
     atmosphere
    1.73
     alive
    1.72
     Vibr
    1.72
     buzz
    1.70
    Activations Density 0.040%

    No Known Activations