© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64669
    Prev
    Next
    INDEX
    Explanations

    choice and options

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

    The neuron is primarily triggered by the occurrence of the token “to,” i.e. it detects the preposition/infinitive marker “to.”

    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
    created
    -0.91
    conflict
    -0.89
     CONSIDER
    -0.88
     Consider
    -0.85
     Considerations
    -0.83
     Conflicts
    -0.82
     Concerns
    -0.81
    consider
    -0.81
    compared
    -0.81
     Consideration
    -0.81
    POSITIVE LOGITS
     choice
    3.39
     choices
    2.84
     choose
    2.30
     choix
    2.09
    choice
    2.05
     chose
    1.84
    Choice
    1.73
     pilihan
    1.72
    choices
    1.71
     Choice
    1.67
    Activations Density 0.049%

    No Known Activations