© 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. 82461
    Prev
    Next
    INDEX
    Explanations

    months in dates

    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
     so
    -1.23
     only
    -1.17
     it
    -1.12
     significant
    -1.09
     any
    -1.06
     every
    -1.00
     people
    -0.98
     Being
    -0.96
     one
    -0.96
     most
    -0.94
    POSITIVE LOGITS
    received
    1.05
     pesquis
    0.98
     všechny
    0.96
    veröffentlichung
    0.96
     referees
    0.96
    zyż
    0.95
     Upside
    0.94
     取り付け
    0.93
    겅
    0.92
    殍
    0.92
    Activations Density 0.104%

    No Known Activations