© 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. 10-GEMMASCOPE-RES-131K
    7. 59574
    Prev
    Next
    INDEX
    Explanations

    actions and ongoing states

    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_10/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
     also
    -1.61
     giorgio
    -1.36
     kablo
    -1.34
     armani
    -1.33
     buatan
    -1.33
     daihatsu
    -1.30
     mondeo
    -1.25
     vectra
    -1.25
     tisch
    -1.24
     wmns
    -1.23
    POSITIVE LOGITS
     étant
    1.48
     sendo
    1.33
    讥
    1.26
     História
    1.25
    ༅
    1.23
    なんですが
    1.22
     Почему
    1.16
    齎
    1.16
     being
    1.16
     solamente
    1.15
    Activations Density 0.124%

    No Known Activations