© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115644
    Prev
    Next
    INDEX
    Explanations

    intensifiers preceding descriptors

    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
     jure
    -1.17
     brillo
    -1.16
    gapi
    -1.12
     pantalon
    -1.11
    quelize
    -1.09
     fondu
    -1.09
     relojes
    -1.05
     rapor
    -1.05
    rably
    -1.05
    これは
    -1.05
    POSITIVE LOGITS
     easier
    1.57
     raining
    1.55
     easy
    1.45
     possible
    1.41
     obvious
    1.38
     snowing
    1.35
     difficult
    1.34
     to
    1.19
     that
    1.18
     evident
    1.16
    Activations Density 0.035%

    No Known Activations