© 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. 55844
    Prev
    Next
    INDEX
    Explanations

    website content

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

    This neuron activates on Czech and Slovak words (i.e. text segments in those languages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     it
    -1.66
     si
    -1.53
     zich
    -1.49
     se
    -1.47
     them
    -1.39
     sich
    -1.33
     се
    -1.14
     are
    -0.99
    Si
    -0.94
     would
    -0.94
    POSITIVE LOGITS
     UnityEngine
    0.92
    ilités
    0.92
     byly
    0.87
    aps
    0.87
     spouse
    0.87
    やってきた
    0.86
     obtend
    0.85
    ныхъ
    0.84
    問合せ
    0.84
    ってない
    0.84
    Activations Density 0.005%

    No Known Activations