© 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. 22-GEMMASCOPE-RES-131K
    7. 11142
    Prev
    Next
    INDEX
    Explanations

    I my ourselves

    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_22/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
     seiner
    -1.85
     his
    -1.84
     suoi
    -1.70
     его
    -1.57
     ему
    -1.52
    ALIAN
    -1.52
     ihrer
    -1.44
     jego
    -1.31
     он
    -1.30
     suyo
    -1.27
    POSITIVE LOGITS
     my
    4.13
     I
    3.50
     our
    3.45
     we
    2.20
     myself
    2.11
     me
    2.00
    our
    1.84
     nossas
    1.84
     ourselves
    1.81
     Our
    1.77
    Activations Density 0.014%

    No Known Activations