© 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. 65478
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases or clauses

    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
     “…
    -1.66
     “
    -1.64
    }}/>
    -1.44
     “.
    -1.36
    “
    -1.34
     “...
    -1.33
     only
    -1.31
    日時
    -1.27
    凜
    -1.26
     while
    -1.24
    POSITIVE LOGITS
     maybe
    2.03
     things
    2.02
     somebody
    1.86
     you
    1.82
     kinda
    1.77
     we
    1.77
     [
    1.76
     stuff
    1.75
     that
    1.73
     väldigt
    1.73
    Activations Density 0.022%

    No Known Activations