© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84074
    Prev
    Next
    INDEX
    Explanations

    choice selection decision

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

    The neuron fires on technical identifiers and numeric labels—e.g. variable names (like “X” or “X_n”), object/property names (e.g. “key value,” “parent.id”), and numeric literals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Meters
    -0.98
    他们的
    -0.94
    ↵↵↵
    -0.90
     CONSIDERATIONS
    -0.90
     rozpoczę
    -0.88
    Calculations
    -0.87
    JsonObject
    -0.85
    盹
    -0.85
    SetBool
    -0.84
     duomen
    -0.84
    POSITIVE LOGITS
     choice
    1.07
     choices
    1.00
     calore
    0.93
     decisions
    0.89
     allegiance
    0.88
     seçim
    0.88
    筮
    0.85
    選択
    0.83
     selection
    0.83
     choosing
    0.82
    Activations Density 0.023%

    No Known Activations