© 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. 34-GEMMASCOPE-RES-131K
    7. 31094
    Prev
    Next
    INDEX
    Explanations

    possessive form of nouns

    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_34/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
     Wordle
    -0.85
    sprache
    -0.84
     Encyclopaedia
    -0.81
     paella
    -0.80
    Alvin
    -0.79
    zőkönyv
    -0.79
    prozess
    -0.79
    СТВ
    -0.79
     Naam
    -0.78
     KEM
    -0.77
    POSITIVE LOGITS
     was
    0.95
    editary
    0.81
    Photo
    0.74
    medium
    0.73
     Introducing
    0.72
    фото
    0.70
     courtesy
    0.68
    by
    0.67
     true
    0.67
     skvě
    0.67
    Activations Density 0.046%

    No Known Activations