© 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. 116796
    Prev
    Next
    INDEX
    Explanations

    favorite and like buttons

    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
     continue
    -1.04
    continue
    -0.94
     stick
    -0.92
    Staying
    -0.91
    Stick
    -0.90
     apsau
    -0.89
     continues
    -0.89
     continuing
    -0.88
     Stick
    -0.86
     продъл
    -0.85
    POSITIVE LOGITS
     already
    1.41
     liked
    1.24
     уже
    1.22
    already
    1.15
    Already
    1.12
     Already
    1.08
     unlike
    1.07
     heart
    1.04
     favorite
    1.03
     좋아
    1.02
    Activations Density 0.014%

    No Known Activations