© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72521
    Prev
    Next
    INDEX
    Explanations

    election and political parties

    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
     ὅ
    -1.48
     chré
    -1.45
    ׇ
    -1.37
     ὑ
    -1.32
     our
    -1.30
    亟
    -1.29
    begingroup
    -1.29
    ITIES
    -1.27
     bershka
    -1.26
     ἐν
    -1.24
    POSITIVE LOGITS
    ּוֹ
    1.83
    ַּ
    1.66
    ִּ
    1.52
    ֶּ
    1.50
    ְּ
    1.40
    rech
    1.33
    ֵּ
    1.33
     party
    1.32
     three
    1.32
    ָּ
    1.30
    Activations Density 0.011%

    No Known Activations