© 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. 116893
    Prev
    Next
    INDEX
    Explanations

    French departments and locations

    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
     remembers
    -1.36
     remembered
    -1.34
     remember
    -1.33
    Remember
    -1.27
     Remember
    -1.27
     remembering
    -1.18
    remember
    -1.16
     recuerdo
    -0.99
     recuerda
    -0.96
     recordó
    -0.95
    POSITIVE LOGITS
    Ű
    0.88
     עי
    0.75
     Upper
    0.73
    </>
    0.73
     decorados
    0.73
    ssan
    0.69
    Lak
    0.69
    lightning
    0.69
    esimo
    0.69
    auce
    0.68
    Activations Density 0.015%

    No Known Activations