© 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. 12269
    Prev
    Next
    INDEX
    Explanations

    used in the event 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
     through
    -1.48
     there
    -1.30
     cultuur
    -1.27
     lehetős
    -1.25
     one
    -1.23
    ってない
    -1.20
     theres
    -1.18
     molesta
    -1.16
    いただき
    -1.13
     mulig
    -1.10
    POSITIVE LOGITS
     to
    1.81
    lysm
    1.64
     purposes
    1.34
     musst
    1.30
    ➶
    1.25
    」
    1.24
    ยม
    1.23
    obtained
    1.21
    度
    1.20
    來
    1.16
    Activations Density 0.282%

    No Known Activations