© 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. 103372
    Prev
    Next
    INDEX
    Explanations

    rustic old wood and exposed metal

    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
     palaces
    -0.89
     perry
    -0.85
    éia
    -0.85
    Classe
    -0.84
     suffers
    -0.84
    żo
    -0.83
    рилл
    -0.83
     Castles
    -0.82
    ecuted
    -0.82
    enyum
    -0.82
    POSITIVE LOGITS
     wood
    1.73
     wooden
    1.71
     rustic
    1.70
     exposed
    1.70
     industrial
    1.55
     reclaimed
    1.53
     vintage
    1.45
     old
    1.41
     metal
    1.36
    Exposed
    1.35
    Activations Density 0.030%

    No Known Activations