© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2161
    Prev
    Next
    INDEX
    Explanations

    delicious food descriptions

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

    delicious and flavorful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    🏩
    0.49
     ЕГЭ
    0.48
     निष्क्रिय
    0.45
     updateConfirm
    0.43
     уважаемые
    0.43
    पतवार
    0.43
    赓
    0.43
     protracted
    0.42
     wrześ
    0.42
     disillusioned
    0.42
    POSITIVE LOGITS
     맛있
    1.99
     delicious
    1.96
     tasty
    1.91
    delicious
    1.85
    美味
    1.76
     flavorful
    1.76
     scrumptious
    1.73
     맛
    1.71
     вкус
    1.70
     delicioso
    1.70
    Activations Density 0.839%

    No Known Activations