© 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. 59336
    Prev
    Next
    INDEX
    Explanations

    starting parenthesis

    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
     his
    -1.33
     jego
    -1.12
     его
    -1.06
     peluche
    -1.05
     suoi
    -1.04
     bluza
    -1.04
    Ii
    -1.01
     Универ
    -1.01
     eksemp
    -1.00
     éton
    -0.99
    POSITIVE LOGITS
     simply
    0.94
     have
    0.92
    权益
    0.89
     achieving
    0.88
     должен
    0.84
    Réalisation
    0.84
    汶
    0.84
     new
    0.82
    ),
    0.82
     having
    0.82
    Activations Density 0.013%

    No Known Activations