© 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. 34-GEMMASCOPE-RES-131K
    7. 78978
    Prev
    Next
    INDEX
    Explanations

    picture and descriptive text

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

    The neuron responds to numeric data and key fact labels (e.g. population figures, area, “municipality,” “province,” etc.) as one would find in a geographic infobox.

    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
    História
    -0.75
    蚓
    -0.75
    これも
    -0.70
    彰化
    -0.69
     zwykle
    -0.68
    isata
    -0.67
     COUNTRIES
    -0.66
     vemos
    -0.66
    ोजना
    -0.65
    ktar
    -0.65
    POSITIVE LOGITS
     alterations
    0.90
    蒴
    0.84
     desayuno
    0.83
     Alter
    0.79
     Memphis
    0.78
    CRO
    0.78
     سوق
    0.77
     UNF
    0.77
    蜓
    0.77
     BREAK
    0.76
    Activations Density 0.010%

    No Known Activations