© 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. 103767
    Prev
    Next
    INDEX
    Explanations

    in a way

    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
    seau
    -1.01
    oniec
    -0.96
     maanden
    -0.93
    APIS
    -0.91
    jw
    -0.89
     одного
    -0.88
     некоторых
    -0.87
    któ
    -0.86
     //$
    -0.85
    ί
    -0.84
    POSITIVE LOGITS
     ways
    3.33
     a
    3.22
     way
    2.64
     manner
    2.36
     such
    2.31
     manière
    2.17
    Ways
    2.14
     sposób
    2.02
     Ways
    1.91
     façon
    1.89
    Activations Density 0.105%

    No Known Activations