© 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. 95476
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
     snabbt
    -1.13
    👸
    -1.12
     سيكون
    -1.11
     zweier
    -1.06
     vanligt
    -1.06
     nästan
    -1.06
     nadat
    -1.03
    亵
    -1.02
     pertes
    -1.02
    忍受
    -1.01
    POSITIVE LOGITS
     our
    1.63
    bufio
    1.57
     what
    1.41
     today
    1.34
     my
    1.32
     we
    1.27
     so
    1.27
    できるので
    1.24
     therefore
    1.23
    を書
    1.23
    Activations Density 0.007%

    No Known Activations