© 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. 33043
    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
     saka
    -1.22
     vek
    -1.15
     concetto
    -1.13
     actualité
    -1.13
     burbu
    -1.09
    strukt
    -1.09
    moderne
    -1.09
     intelig
    -1.06
     kuah
    -1.06
    unggah
    -1.05
    POSITIVE LOGITS
    u
    1.25
    ena
    1.18
     mężczyzn
    1.09
    subplots
    1.08
    e
    1.07
    值
    1.06
    case
    1.05
    ,'
    1.03
    ens
    1.03
    br
    1.02
    Activations Density 0.006%

    No Known Activations