© 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. 25843
    Prev
    Next
    INDEX
    Explanations

    previous times or states

    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
     another
    -1.13
     לאחר
    -0.96
     continue
    -0.92
    iedene
    -0.91
     zukünf
    -0.91
    他又
    -0.89
     once
    -0.89
     después
    -0.88
     continues
    -0.88
     continuer
    -0.87
    POSITIVE LOGITS
     existed
    1.31
     this
    1.27
     existence
    1.21
     arrival
    1.20
     recent
    1.20
    recent
    1.08
    exists
    1.05
    existence
    1.03
     current
    0.98
     intervention
    0.98
    Activations Density 0.051%

    No Known Activations