© 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. 128746
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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
     sendero
    -1.10
    おわりに
    -1.10
    她和
    -1.09
     terceiro
    -1.09
     jei
    -1.05
     chaleco
    -1.05
     universitaria
    -1.02
    ブログ村
    -1.00
    えっ
    -1.00
     iſt
    -0.97
    POSITIVE LOGITS
    ATED
    0.99
    но
    0.97
    consola
    0.93
     când
    0.93
     însă
    0.92
    ü
    0.91
    ных
    0.91
    ION
    0.91
    ING
    0.90
     affidavit
    0.90
    Activations Density 0.034%

    No Known Activations