© 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. 63717
    Prev
    Next
    INDEX
    Explanations

    in + [word]

    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
     however
    -1.89
    }$.
    -1.58
     البته
    -1.46
     cependant
    -1.45
    そして
    -1.44
     также
    -1.43
    ただし
    -1.43
    しかし
    -1.41
    прочем
    -1.36
    ちなみに
    -1.35
    POSITIVE LOGITS
     By
    1.07
    某些
    1.05
    Very
    1.02
    Regardless
    1.02
     منذ
    1.00
     хочешь
    0.99
    //!
    0.97
    っているので
    0.95
    為に
    0.95
     With
    0.95
    Activations Density 0.128%

    No Known Activations