© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22264
    Prev
    Next
    INDEX
    Explanations

    Finnish

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

    The main thing this neuron does is detect references to Finland or Finnish-related terms (e.g., “Finnish,” “Finland,” Finnish place and person names).

    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
     the
    -1.42
     verschiedenen
    -1.36
     jälkeen
    -1.34
     kirj
    -1.33
     peluang
    -1.31
     unterschied
    -1.30
     verschiedener
    -1.29
    medriver
    -1.29
     kyllä
    -1.29
    raseña
    -1.28
    POSITIVE LOGITS
     Finnish
    1.52
    \}$,
    1.47
    Finnish
    1.45
    Finland
    1.44
     воспользоваться
    1.30
     recompensa
    1.27
    ”，
    1.27
    ↵↵↵
    1.26
     turista
    1.25
     lanterna
    1.23
    Activations Density 0.083%

    No Known Activations