© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6252
    Prev
    Next
    INDEX
    Explanations

    creatures, monsters, and beings

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

    This neuron responds to content-bearing words—especially nouns, adjectives, and other semantically rich tokens used in descriptive narrative.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aftermarket
    0.55
    凿
    0.55
    📵
    0.55
     lottery
    0.54
    禊
    0.54
    낚
    0.53
     окон
    0.52
     extrac
    0.52
     thác
    0.52
     adulter
    0.51
    POSITIVE LOGITS
     creature
    1.47
     creatures
    1.36
     Creature
    1.25
     humanoid
    1.20
     furry
    1.14
     Creatures
    1.13
     beast
    1.10
     criaturas
    1.10
    牠
    1.09
    animal
    1.07
    Activations Density 0.731%

    No Known Activations