© 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. 49997
    Prev
    Next
    INDEX
    Explanations

    introduction of contrasting ideas

    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
     universite
    -1.35
    Again
    -1.27
    Therefore
    -1.20
    ⁸
    -1.18
     hierv
    -1.17
    豳
    -1.13
    again
    -1.09
     wła
    -1.09
    ʺ
    -1.09
    //}
    
    -1.09
    POSITIVE LOGITS
     that
    2.20
     while
    2.19
     there
    2.17
     it
    2.16
     according
    1.79
     despite
    1.67
     amid
    1.65
     with
    1.56
     nothing
    1.48
     things
    1.47
    Activations Density 0.055%

    No Known Activations