© 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. 117098
    Prev
    Next
    INDEX
    Explanations

    getting object properties

    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
    韪
    -1.33
    焄
    -1.14
    宝马
    -1.10
    unless
    -1.04
    Dimanche
    -1.01
    Genial
    -1.00
     unless
    -1.00
    this
    -0.99
    Răsp
    -0.98
    却被
    -0.97
    POSITIVE LOGITS
    xce
    0.95
    cT
    0.95
     from
    0.93
    谏
    0.93
    țin
    0.93
     kwiet
    0.92
    rashed
    0.91
     naprawdę
    0.91
     started
    0.90
    GEBRA
    0.89
    Activations Density 0.012%

    No Known Activations