© 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. 119013
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specifically detects Italian-language tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     halte
    -1.44
    ramid
    -1.30
    Så
    -1.19
    drei
    -1.19
     gonzález
    -1.18
     labai
    -1.17
     teater
    -1.16
     öde
    -1.16
     only
    -1.15
    Dette
    -1.13
    POSITIVE LOGITS
     again
    1.59
     during
    1.52
     your
    1.46
     for
    1.42
    nadequate
    1.38
     včetně
    1.35
     since
    1.33
    DeleteCommand
    1.33
     room
    1.27
     his
    1.25
    Activations Density 0.010%

    No Known Activations