© 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. 10-GEMMASCOPE-RES-131K
    7. 1469
    Prev
    Next
    INDEX
    Explanations

    what kind of

    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
     également
    -1.35
    aktery
    -1.23
    )))),
    -1.18
    Activité
    -1.16
    usine
    -1.14
    ransition
    -1.14
    erschrank
    -1.11
    lakukan
    -1.09
     guerre
    -1.09
     einigen
    -1.09
    POSITIVE LOGITS
    纔
    1.51
     Personalis
    1.32
     this
    1.27
     perdeu
    1.25
    
    1.23
     왕
    1.20
     tull
    1.16
    っております
    1.16
    PARTIC
    1.13
    就没
    1.13
    Activations Density 0.021%

    No Known Activations