© 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. 59187
    Prev
    Next
    INDEX
    Explanations

    your custom attributes

    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
     Dinas
    -1.34
     élas
    -1.30
     étan
    -1.27
     inond
    -1.19
     mété
    -1.17
     vener
    -1.17
    Itu
    -1.09
     perpé
    -1.09
    ebly
    -1.08
    
    -1.08
    POSITIVE LOGITS
     our
    1.89
     from
    1.47
     your
    1.36
     or
    1.35
     both
    1.34
     all
    1.28
     there
    1.27
     unserer
    1.27
     without
    1.27
     other
    1.25
    Activations Density 0.171%

    No Known Activations