© 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. 23490
    Prev
    Next
    INDEX
    Explanations

    citations with numbers

    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
     a
    -1.58
     that
    -1.56
     there
    -1.33
     even
    -1.23
     or
    -1.23
     and
    -1.22
     what
    -1.20
     essential
    -1.20
     it
    -1.18
    There
    -1.17
    POSITIVE LOGITS
     contenir
    1.37
     siè
    1.35
    潆
    1.31
     diriger
    1.27
     terminer
    1.27
     précédent
    1.22
     aient
    1.21
    还是很
    1.18
     réduire
    1.17
    鸸
    1.17
    Activations Density 0.064%

    No Known Activations