© 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. 101732
    Prev
    Next
    INDEX
    Explanations

    commands to leave or stay away

    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
     edile
    -1.23
     Arhi
    -1.23
     rafra
    -1.21
    笳
    -1.19
     perdre
    -1.18
     superbes
    -1.16
     that
    -1.15
    llte
    -1.14
     hoj
    -1.14
     bonos
    -1.13
    POSITIVE LOGITS
     I
    1.47
     s
    1.27
     l
    1.23
     any
    1.20
     wią
    1.18
     m
    1.16
     it
    1.15
     my
    1.12
     w
    1.11
     in
    1.09
    Activations Density 0.034%

    No Known Activations