© 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. 98699
    Prev
    Next
    INDEX
    Explanations

    one and the other

    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
     that
    -1.19
     their
    -1.08
     the
    -1.02
     all
    -1.01
    ."
    -0.98
    itel
    -0.96
     these
    -0.96
     what
    -0.93
     our
    -0.91
     menjal
    -0.90
    POSITIVE LOGITS
     others
    1.66
     then
    1.59
     secondly
    1.29
     دیگری
    1.23
    others
    1.17
    Others
    1.09
     másik
    1.04
    桠
    1.00
     другое
    1.00
    autre
    0.98
    Activations Density 0.085%

    No Known Activations