© 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. 47693
    Prev
    Next
    INDEX
    Explanations

    food and recipes

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

    The neuron is essentially picking up on how common or frequent a token is (i.e. it yields high activations for words that occur very often in the text).

    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
    カロリー
    -0.90
    ִּ
    -0.89
    ów
    -0.86
    Calories
    -0.82
     membunuh
    -0.81
    currentUser
    -0.81
    Traducción
    -0.81
     configurable
    -0.79
    zten
    -0.77
    bestos
    -0.77
    POSITIVE LOGITS
     cocktails
    1.34
     baking
    1.32
     salads
    1.27
     added
    1.27
     use
    1.20
     adding
    1.16
    baking
    1.13
     soup
    1.11
     recipes
    1.09
     applications
    1.08
    Activations Density 0.031%

    No Known Activations