© 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. 119053
    Prev
    Next
    INDEX
    Explanations

    what it means

    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
    simply
    -0.90
    هم
    -0.90
     gewüns
    -0.88
    只有
    -0.87
    obviously
    -0.86
    使用
    -0.86
     siempre
    -0.84
    Peer
    -0.83
    always
    -0.83
    given
    -0.83
    POSITIVE LOGITS
     entails
    1.95
     means
    1.69
     mean
    1.66
     entail
    1.58
     entailed
    1.56
     meant
    1.33
     look
    1.33
     looks
    1.24
     looked
    1.22
     consisted
    1.21
    Activations Density 0.031%

    No Known Activations