© 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. 65706
    Prev
    Next
    INDEX
    Explanations

    topography and spatial description

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

    The neuron fires strongly on any mention of “topo”-rooted terms—e.g. topography, topographic, topographical—i.e. words referring to terrain or mapping of surface features.

    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
     Übersetzungen
    -2.14
     avesse
    -2.09
    ?"
    -2.05
    渽
    -2.02
     undergoes
    -2.02
    л
    -2.02
     augen
    -1.99
    .")
    -1.99
     betreff
    -1.96
     affords
    -1.95
    POSITIVE LOGITS
    喾
    2.63
     obsessive
    2.19
    REVISTA
    2.17
    徬
    2.17
     unsere
    2.17
     nourriture
    2.14
     impede
    2.11
    槩
    2.11
     svart
    2.06
     intensify
    2.06
    Activations Density 0.008%

    No Known Activations