© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16448
    Prev
    Next
    INDEX
    Explanations

    political parties and alignments

    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
     acquist
    -1.38
     reele
    -1.28
     indywidual
    -1.27
    Kommentar
    -1.24
    ----</
    -1.24
    asztok
    -1.22
    賸
    -1.22
     مباراة
    -1.21
    معلومات
    -1.20
     botanique
    -1.20
    POSITIVE LOGITS
     Green
    1.38
     anti
    1.34
     Wall
    1.28
     Broad
    1.25
     we
    1.21
     White
    1.16
     junger
    1.14
     party
    1.13
     not
    1.13
     Bear
    1.12
    Activations Density 0.070%

    No Known Activations