© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1465
    Prev
    Next
    INDEX
    Explanations

    names of people and companies

    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
    ุ
    -0.72
    
    -0.70
    Gruß
    -0.68
    وید
    -0.68
     liście
    -0.68
    テン
    -0.68
    grav
    -0.64
    пру
    -0.64
    GRADE
    -0.63
     Rabu
    -0.63
    POSITIVE LOGITS
     Bloom
    1.52
     bloom
    1.21
     sketch
    1.13
    Bloom
    1.10
    sketch
    1.09
     hash
    1.09
     sketching
    1.06
    Hash
    1.05
    bloom
    1.00
     BLOOM
    1.00
    Activations Density 0.028%

    No Known Activations