© 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. 81307
    Prev
    Next
    INDEX
    Explanations

    changes and transitions

    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
    tiennent
    -0.84
     wayward
    -0.82
     Ghi
    -0.82
     stalemate
    -0.80
    YSTAL
    -0.79
     resurgence
    -0.79
    גב
    -0.77
    τικός
    -0.77
     Sludge
    -0.76
    mektedir
    -0.76
    POSITIVE LOGITS
     disruption
    3.52
     disruptive
    2.83
     disrupt
    2.78
     disrupting
    2.77
     disruptions
    2.75
     upheaval
    2.66
     disrupted
    2.55
     upro
    1.92
     destabili
    1.89
     dislocation
    1.86
    Activations Density 0.042%

    No Known Activations