© 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. 67083
    Prev
    Next
    INDEX
    Explanations

    information related concepts

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

    This neuron responds to the term “information” (and closely related compounds like information management, information services, information record, etc.).

    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
     mehrere
    -1.87
    úd
    -1.72
     страны
    -1.66
     impetus
    -1.63
    begin
    -1.62
     schilder
    -1.59
    écial
    -1.59
     enormes
    -1.55
    ,'
    -1.55
     hallowed
    -1.54
    POSITIVE LOGITS
    .
    2.41
    n
    1.84
    踅
    1.83
    information
    1.59
     Then
    1.58
    把它
    1.57
     informativo
    1.55
     
    1.52
     For
    1.51
     soltanto
    1.47
    Activations Density 0.025%

    No Known Activations