© 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. 70035
    Prev
    Next
    INDEX
    Explanations

    roomsspacesbuildings

    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
     افزایش
    -0.90
     downtown
    -0.88
    HideFlags
    -0.85
     thatched
    -0.82
     castles
    -0.79
    እ
    -0.78
    家に
    -0.77
     ranch
    -0.77
    Melody
    -0.76
     accompan
    -0.76
    POSITIVE LOGITS
     courtyard
    1.20
     gallery
    1.02
     court
    1.02
     hall
    1.01
     chamber
    1.00
     galleries
    1.00
     Drawing
    0.96
     Reception
    0.95
     Gallery
    0.95
     Court
    0.91
    Activations Density 0.024%

    No Known Activations