© 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. 102598
    Prev
    Next
    INDEX
    Explanations

    returning and improving

    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
    ICHT
    -1.02
     ďal
    -0.98
    REMOVE
    -0.94
    Ⓔ
    -0.90
    letto
    -0.87
     који
    -0.86
    __.__
    -0.85
    のに
    -0.85
    marginLeft
    -0.84
     erity
    -0.84
    POSITIVE LOGITS
     stronger
    3.47
     wiser
    2.75
     richer
    2.61
     bigger
    2.38
     Stronger
    2.34
     smarter
    2.23
     better
    2.20
     healthier
    2.19
     brighter
    2.13
     taller
    2.06
    Activations Density 0.054%

    No Known Activations