© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76278
    Prev
    Next
    INDEX
    Explanations

    aliases or nicknames

    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
    ższych
    -0.98
     fiecare
    -0.90
     Když
    -0.88
    锉
    -0.88
    horloge
    -0.85
     khóa
    -0.83
     Při
    -0.82
     サム
    -0.82
     împre
    -0.82
    嘸
    -0.81
    POSITIVE LOGITS
     Mr
    2.31
     Captain
    1.73
    Mr
    1.63
     Mister
    1.57
     Professor
    1.54
     Miss
    1.54
     Uncle
    1.54
     Dr
    1.51
     Monsieur
    1.46
     mr
    1.45
    Activations Density 0.126%

    No Known Activations